Peer Revenue An exchange of ideas

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computation and Language

cs.CL Watch Computation and Language

Tuesday 14 April

Computation and Language

Agentic Insight Generation in VSM Simulations

Micha Selak, Dirk Krechel, Adrian Ulges et al. (+3 more)

Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new avenues to support users with this task. While existing approaches excel at processing raw data to gain information, they are structurally unfit to pick up on subtle situational differences needed to distinguish similar data sources in this domain. To address this issue, we propose a decoupled, two-step agentic architecture. By separating orchestration from data analysis, the system leverages progressive data discovery infused with domain expert knowledge. This architecture allows the orchestration to intelligently select data sources and perform multi-hop reasoning across data structures while maintaining a slim internal context. Results from multiple state-of-the-art large language models demonstrate the framework's viability: with top-tier models achieving accuracies of up to 86% and demonstrating high robustness across evaluation runs.
Read the full abstract

All authors Micha Selak, Dirk Krechel, Adrian Ulges, Sven Spieckermann, Niklas Stoehr, Andreas Loehr

Computation and Language

KoCo: Conditioning Language Model Pre-training on Knowledge Coordinates

Yudong Li, Jiawei Cai and Linlin Shen

Standard Large Language Model (LLM) pre-training typically treats corpora as flattened token sequences, often overlooking the real-world context that humans naturally rely on to contextualize information. To bridge this gap, we introduce Knowledge Coordinate Conditioning (KoCo), a simple method that maps every document into a three-dimensional semantic coordinate. By prepending these coordinates as textual prefixes for pre-training, we aim to equip the model with explicit contextual awareness to learn the documents within the real-world knowledge structure. Experiment results demonstrate that KoCo significantly enhances performance across 10 downstream tasks and accelerates pre-training convergence by approximately 30%. Furthermore, our analysis indicates that explicitly modeling knowledge coordinates helps the model distinguish stable facts from noise, effectively mitigating hallucination in generated outputs.
Read the full abstract

Computation and Language

From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue

Jiarui Zhang, Xiangyu Liu, Yong Hu et al. (+5 more)

Multi-turn dialogue is the predominant form of interaction with large language models (LLMs). While LLM routing is effective in single-turn settings, existing methods fail to maximize cumulative performance in multi-turn dialogue due to interaction dynamics and delayed rewards. To address this challenge, we move from myopic, single-turn selection to long-horizon sequential routing for multi-turn dialogue. Accordingly, we propose DialRouter, which first performs MCTS to explore dialogue branches induced by different LLM selections and collect trajectories with high cumulative rewards. DialRouter then learns a lightweight routing policy from search-derived data, augmented with retrieval-based future state approximation, enabling multi-turn routing without online search. Experiments on both open-domain and domain-specific dialogue tasks across diverse candidate sets of both open-source and closed-source LLMs demonstrate that DialRouter significantly outperforms single LLMs and existing routing baselines in task success rate, while achieving a superior performance-cost trade-off when combined with a cost-aware reward.
Read the full abstract

All authors Jiarui Zhang, Xiangyu Liu, Yong Hu, Chaoyue Niu, Hang Zeng, Shaojie Tang, Fan Wu, Guihai Chen

Computation and Language

ReasonXL: A Large-Scale Corpus for Language-Specific Reasoning in LLMs

Daniil Gurgurov, Tom Röhr, Sebastian von Rohrscheidt et al. (+3 more)

Despite advances in multilingual capabilities, most large language models (LLMs) remain English-centric in their training and, crucially, in the reasoning traces they produce: even for non-English problems, they predominantly reason in English, leaving non-English users with intermediate reasoning they cannot follow. We address this disparity with two contributions. **(a)** We introduce $\texttt{ReasonXL}$, the first large-scale parallel corpus of cross-domain reasoning traces in five European languages (English, German, French, Italian, and Spanish): over 2.5M aligned samples (11B tokens) per language, each comprising prompt, reasoning trace, and final output, enabling direct supervision of language-specific reasoning. **(b)** Using $\texttt{ReasonXL}$, we demonstrate that LLMs can be adapted to reason entirely in a target language through a simple two-stage pipeline of supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR), matching or exceeding the base models' English-reasoning performance in two of four languages and recovering most of it in the remaining two.
Read the full abstract

All authors Daniil Gurgurov, Tom Röhr, Sebastian von Rohrscheidt, Josef van Genabith, Alexander Löser, Simon Ostermann

Computation and Language

SCRIPT: A Subcharacter Compositional Representation Injection Module for Korean Pre-Trained Language Models

SungHo Kim, Juhyeong Park, Eda Atalay et al. (+1 more)

Korean is a morphologically rich language with a featural writing system in which each character is systematically composed of subcharacter units known as Jamo. These subcharacters not only determine the visual structure of Korean but also encode frequent and linguistically meaningful morphophonological processes. However, most current Korean language models (LMs) are based on subword tokenization schemes, which are not explicitly designed to capture the internal compositional structure of characters. To address this limitation, we propose SCRIPT, a model-agnostic module that injects subcharacter compositional knowledge into Korean PLMs. SCRIPT allows to enhance subword embeddings with structural granularity, without requiring architectural changes or additional pre-training. As a result, SCRIPT enhances all baselines across various Korean natural language understanding (NLU) and generation (NLG) tasks. Moreover, beyond performance gains, detailed linguistic analyses show that SCRIPT reshapes the embedding space in a way that better captures grammatical regularities and semantically cohesive variations. Our code is available at https://github.com/SungHo3268/SCRIPT.
Read the full abstract

All authors SungHo Kim, Juhyeong Park, Eda Atalay, SangKeun Lee

Computation and Language

Cooperative Memory Paging with Keyword Bookmarks for Long-Horizon LLM Conversations

Ziyang Liu

When LLM conversations grow beyond the context window, old content must be evicted – but how does the model recover it when needed? We propose cooperative paging: evicted segments are replaced with minimal keyword bookmarks ([pN:keywords], ~8-24 tokens each), and the model is given a recall() tool to retrieve full content on demand. On the LoCoMo benchmark (10 real multi-session conversations, 300+ turns), cooperative paging achieves the highest answer quality among six methods – outperforming truncation, BM25, word-overlap retrieval, a search-tool baseline, and full context – on four models (GPT-4o-mini, DeepSeek-v3.2, Claude Haiku, GLM-5), confirmed by four independent LLM judges ($p=0.017$, paired bootstrap). We then study the paging design space with a 5x4 ablation over boundary strategies and eviction policies (3,176 synthetic probes, 1,600 LoCoMo probes). Key findings: (1) coarse fixed-size pages (fixed_20) reach 96.7% while content-aware topic_shift collapses to 56.7%; (2) eviction policy choice is data-dependent (FIFO best on synthetic, LFU on LoCoMo); (3) two bookmark generation strategies improve over the heuristic baseline (+4.4 and +8.7 E2E points); (4) the remaining bottleneck is bookmark discrimination – the model triggers recall() 96% of the time but selects the correct page only 57% when bookmarks are insufficiently distinctive. Keyword specificity alone accounts for a 25 percentage point accuracy difference.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

NVIDIA: Aakshita Chandiramani, Aaron Blakeman, Abdullahi Olaoye et al. (+542 more)

We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemotron 3 Super is the first model in the Nemotron 3 family to 1) be pre-trained in NVFP4, 2) leverage LatentMoE, a new Mixture-of-Experts architecture that optimizes for both accuracy per FLOP and accuracy per parameter, and 3) include MTP layers for inference acceleration through native speculative decoding. We pre-trained Nemotron 3 Super on 25 trillion tokens followed by post-training using supervised fine tuning (SFT) and reinforcement learning (RL). The final model supports up to 1M context length and achieves comparable accuracy on common benchmarks, while also achieving up to 2.2x and 7.5x higher inference throughput compared to GPT-OSS-120B and Qwen3.5-122B, respectively. Nemotron 3 Super datasets, along with the base, post-trained, and quantized checkpoints, are open-sourced on HuggingFace.
Read the full abstract

All authors NVIDIA: Aakshita Chandiramani, Aaron Blakeman, Abdullahi Olaoye, Abhibha Gupta, Abhilash Somasamudramath, Abhinav Khattar, Adeola Adesoba, Adi Renduchintala, Adil Asif, Aditya Agrawal, Aditya Vavre, Ahmad Kiswani, Aishwarya Padmakumar, Ajay Hotchandani, Akanksha Shukla, Akhiad Bercovich, Aleksander Ficek, Aleksandr Shaposhnikov, Alex Gronskiy, Alex Kondratenko, Alex Neefus, Alex Steiner, Alex Yang, Alexander Bukharin, Alexander Young, Ali Hatamizadeh, Ali Taghibakhshi, Alina Galiautdinova, Alisa Liu, Alok Kumar, Ameya Sunil Mahabaleshwarkar, Amir Klein, Amit Zuker, Amnon Geifman, Anahita Bhiwandiwalla, Ananth Subramaniam, Andrew Tao, Anjaney Shrivastava, Anjulie Agrusa, Ankur Srivastava, Ankur Verma, Ann Guan, Anna Shors, Annamalai Chockalingam, Anubhav Mandarwal, Aparnaa Ramani, Arham Mehta, Arti Jain, Arun Venkatesan, Asha Anoosheh, Ashwath Aithal, Ashwin Poojary, Asif Ahamed, Asit Mishra, Asli Sabanci Demiroz, Asma Kuriparambil Thekkumpate, Atefeh Sohrabizadeh, Avinash Kaur, Ayush Dattagupta, Barath Subramaniam Anandan, Bardiya Sadeghi, Barnaby Simkin, Ben Lanir, Benedikt Schifferer, Benjamin Chislett, Besmira Nushi, Bilal Kartal, Bill Thiede, Bita Darvish Rouhani, Bobby Chen, Boris Ginsburg, Brandon Norick, Branislav Kisacanin, Brian Yu, Bryan Catanzaro, Buvaneswari Mani, Carlo del Mundo, Chankyu Lee, Chanran Kim, Chantal Hwang, Chao Ni, Charles Wang, Charlie Truong, Cheng-Ping Hsieh, Chenhan Yu, Chenjie Luo, Cherie Wang, Chetan Mungekar, Chintan Patel, Chris Alexiuk, Chris Holguin, Chris Wing, Christian Munley, Christopher Parisien, Chuck Desai, Chunyang Sheng, Collin Neale, Cyril Meurillon, Dakshi Kumar, Dan Gil, Dan Su, Dane Corneil, Daniel Afrimi, Daniel Burkhardt Eliuth Triana, Daniel Egert, Daniel Fatade, Daniel Lo, Daniel Rohrer, Daniel Serebrenik, Daniil Sorokin, Daria Gitman, Daria Levy, Darko Stosic, David Edelsohn, David Messina, David Mosallanezhad, David Tamok, Deena Donia, Deepak Narayanan, Devin O'Kelly, Dheeraj Peri, Dhruv Nathawani, Di Wu, Dima Rekesh, Dina Yared, Divyanshu Kakwani, Dmitry Konyagin Brandon Tuttle, Dong Ahn, Dongfu Jiang, Dorrin Poorkay, Douglas O'Flaherty, Duncan Riach, Dusan Stosic, Dustin Van Stee, Edgar Minasyan, Edward Lin, Eileen Peters Long, Elad Segal, Elena Lantz, Elena Lewis, Ellie Evans, Elliott Ning, Eric Chung, Eric Harper, Eric Pham-Hung, Eric W. Tramel, Erick Galinkin, Erik Pounds, Esti Etrog, Evan Briones, Evan Wu, Evelina Bakhturina, Evgeny Tsykunov, Ewa Dobrowolska, Farshad Saberi Movahed, Farzan Memarian, Fay Wang, Fei Jia, Felipe Soares, Felipe Vieira Frujeri, Feng Chen, Fengguang Lin, Ferenc Galko, Fortuna Zhang, Frankie Siino, Frida Hou, Gantavya Bhatt, Gargi Prasad, Geethapriya Venkataramani, Geetika Gupta, George Armstrong, Gerald Shen, Giulio Borghesi, Gordana Neskovic, Gorkem Batmaz, Grace Lam, Grace Wu, Greg Pauloski, Greyson Davis, Grigor Nalbandyan, Guoming Zhang, Guy Farber, Guyue Huang, Haifeng Qian, Haran Kumar Shiv Kumar, Harry Kim, Harsh Sharma, Hayate Iso, Hayley Ross, Herbert Hum, Herman Sahota, Hexin Wang, Himanshu Soni, Hiren Upadhyay, Huy Nguyen, Iain Cunningham, Ido Galil, Ido Shahaf, Igino Padovani, Igor Gitman, Igor Shovkun, Ikroop Dhillon, Ilya Loshchilov, Ingrid Kelly, Itamar Schen, Itay Levy, Ivan Moshkov, Izik Golan, Izzy Putterman, Jain Tu, Jan Baczek, Jan Kautz, Jane Polak Scowcroft, Janica Rosenberg, Jared Casper, Jarrod Pflum, Jason Grant, Jason Sewall, Jatin Mitra, Jeffrey Glick, Jenny Chen, Jesse Oliver, Jiacheng Xu, Jiafan Zhu, Jialin Song, Jian Zhang, Jiaqi Zeng, Jie Lou, Jill Milton, Jim Chow, Jimmy Zhang, Jinhang Choi, Jining Huang, Jocelyn Huang, Joel Caruso, Joey Conway, Joey Guman, Johan Jatko, John Kamalu, Johnny Greco, Jonathan Cohen, Jonathan Raiman, Joseph Jennings, Joyjit Daw, Juan Yu, Julio Tapia, Junkeun Yi, Jupinder Parmar, Jyothi Achar, Kari Briski, Kartik Mattoo, Katherine Cheung, Katherine Luna, Keith Wyss, Kevin Shih, Kezhi Kong, Khanh Nguyen, Khushi Bhardwaj, Kirill Buryak, Kirthi Shankar Sivamani, Konstantinos Krommydas, Kris Murphy, Krishna C. Puvvada, Krzysztof Pawelec, Kumar Anik, Laikh Tewari, Laya Sleiman, Leo Du, Leon Derczynski, Li Ding, Lilach Ilan, Lingjie Wu, Lizzie Wei, Luis Vega, Lun Su, Maarten Van Segbroeck, Maer Rodrigues de Melo, Magaret Zhang, Mahan Fathi, Makesh Narsimhan Sreedhar, Makesh Sreedhar, Makesh Tarun Chandran, Manuel Reyes Gomez, Maor Ashkenazi, Marc Cuevas, Marc Romeijn, Margaret Zhang, Mark Cai, Mark Gabel, Markus Kliegl, Martyna Patelka, Maryam Moosaei, Matthew Varacalli, Matvei Novikov, Mauricio Ferrato, Mehrzad Samadi, Melissa Corpuz, Meng Xin, Mengdi Wang, Mengru Wang, Meredith Price, Micah Schaffer, Michael Andersch, Michael Boone, Michael Evans, Michael Z Wang, Miguel Martinez, Mikail Khona, Mike Chrzanowski, Mike Hollinger, Mingyuan Ma, Minseok Lee, Mohammad Dabbah, Mohammad Shoeybi, Mostofa Patwary, Nabin Mulepati, Nader Khalil, Najeeb Nabwani, Nancy Agarwal, Nanthini Balasubramaniam, Narimane Hennouni, Narsi Kodukula, Natalie Hereth, Nathaniel Pinckney, Nave Assaf, Negar Habibi, Nestor Qin, Neta Zmora, Netanel Haber, Nick Reamaroon, Nickson Quak, Nidhi Bhatia, Nikhil Jukar, Nikki Pope, Nikolai Ludwig, Nima Tajbakhsh, Nir Ailon, Nirmal Juluru, Nirmalya De, Nowel Pitt, Oleg Rybakov, Oleksii Hrinchuk, Oleksii Kuchaiev, Olivier Delalleau, Oluwatobi Olabiyi, Omer Ullman Argov, Omri Almog, Omri Puny, Oren Tropp, Otavio Padovani, Ouye Xie, Parth Chadha, Pasha Shamis, Paul Gibbons, Pavlo Molchanov, Peter Belcak, Peter Jin, Pinky Xu, Piotr Januszewski, Pooya Jannaty, Prachi Shevate, Pradeep Thalasta, Pranav Prashant Thombre, Prasoon Varshney, Prerana Gambhir, Pritam Gundecha, Przemek Tredak, Qing Miao, Qiyu Wan, Quan Tran Minh, Rabeeh Karimi Mahabadi, Rachel Oberman, Rachit Garg, Rahul Kandu, Raina Zhong, Ran El-Yaniv, Ran Zilberstein, Rasoul Shafipour, Renee Yao, Renjie Pi, Richard Mazzarese, Richard Wang, Rick Izzo, Ridhima Singla, Rima Shahbazyan, Rishabh Garg, Ritika Borkar, Ritu Gala, Riyad Islam, Robert Clark, Robert Hesse, Roger Waleffe, Rohit Varma Kalidindi, Rohit Watve, Roi Koren, Ron Fan, Ruchika Kharwar, Ruisi Cai, Ruoxi Zhang, Russell J. Hewett, Ryan Prenger, Ryan Timbrook, Ryota Egashira, Sadegh Mahdavi, Sagar Singh Ashutosh Joshi, Sahil Modi, Samuel Kriman, Sandeep Pombra, Sanjay Kariyappa, Sanjeev Satheesh, Santiago Pombo, Saori Kaji, Satish Pasumarthi, Saurav Mishra, Saurav Muralidharan, Scott Hara, Sean Narenthiran, Sebastian Rogawski, Seonjin Na, Seonmyeong Bak, Sepehr Sameni, Seth Poulos, Shahar Mor, Shantanu Acharya, Shaona Ghosh Adam Lord, Sharath Turuvekere Sreenivas, Shaun Kotek, Shaya Gharghabi, Shelby Thomas, Sheng-Chieh Lin, Shibani Likhite, Shiqing Fan, Shiyang Chen, Shreya Gopal, Shrimai Prabhumoye, Shubham Pachori, Shubham Toshniwal, Shuo Zhang, Shuoyang Ding, Shyam Renjith, Shyamala Prayaga, Siddhartha Jain, Simeng Sun, Sirisha Rella, Sirshak Das, Smita Ithape, Sneha Harishchandra S, Somshubra Majumdar, Soumye Singhal, Sri Harsha Singudasu, Sriharsha Niverty, Stas Sergienko, Stefana Gloginic, Stefania Alborghetti, Stephen Ge, Stephen McCullough, Sugam Dipak Devare, Suguna Varshini Velury, Sukrit Rao, Sumeet Kumar Barua, Sunny Gai, Suseella Panguluri, Sushil Koundinyan, Swathi Patnam, Sweta Priyadarshi, Swetha Bhendigeri, Syeda Nahida Akter, Sylendran Arunagiri, Tailling Yuan, Talor Abramovich, Tan Bui, Tan Yu, Terry Kong, Thanh Do, Thomas Gburek, Thorgane Marques, Tiffany Moore, Tijmen Blankevoort, Tim Moon, Timothy Ma, Tiyasa Mitra, Tomasz Grzegorzek, Tomer Asida, Tomer Bar Natan, Tomer Keren, Tomer Ronen, Traian Rebedea, Trenton Starkey, Tugrul Konuk, Twinkle Vashishth, Tyler Condensa, Udi Karpas, Ushnish De, Vahid Noorozi, Vahid Noroozi, Vanshil Atul Shah, Veena Vaidyanathan, Venkat Srinivasan, Venmugil Elango, Victor Cui, Vijay Korthikanti, Vikas Mehta, Virginia Adams, Virginia Wu, Vitaly Kurin, Vitaly Lavrukhin, Vladimir Anisimov, Wan Seo, Wanli Jiang, Wasi Uddin Ahmad, Wei Du, Wei Ping, Wei-Ming Chen, Wendy Quan, Wenliang Dai, Wenwen Gao, Will Jennings, William Zhang, Xiaowei Ren, Xiaowen Xin, Xin Li, Yang Yu, Yangyi Chen, Yaniv Galron, Yashaswi Karnati, Yejin Choi, Yev Meyer, Yi-Fu Wu, Yian Zhang, Ying Lin, Yonatan Geifman, Yonggan Fu, Yoshi Suhara, Youngeun Kwon, Yuan Zhang, Yuki Huang, Zach Moshe, Zhilin Wang, Zhiyu Cheng, Zhongbo Zhu, Zhuolin Yang, Zihan Liu, Zijia Chen, Zijie Yan, Zuhair Ahmed

Computation and Language

Masked by Consensus: Disentangling Privileged Knowledge in LLM Correctness

Tomer Ashuach, Shai Gretz, Yoav Katz et al. (+2 more)

Humans use introspection to evaluate their understanding through private internal states inaccessible to external observers. We investigate whether large language models possess similar privileged knowledge about answer correctness, information unavailable through external observation. We train correctness classifiers on question representations from both a model's own hidden states and external models, testing whether self-representations provide a performance advantage. On standard evaluation, we find no advantage: self-probes perform comparably to peer-model probes. We hypothesize this is due to high inter-model agreement of answer correctness. To isolate genuine privileged knowledge, we evaluate on disagreement subsets, where models produce conflicting predictions. Here, we discover domain-specific privileged knowledge: self-representations consistently outperform peer representations in factual knowledge tasks, but show no advantage in math reasoning. We further localize this domain asymmetry across model layers, finding that the factual advantage emerges progressively from early-to-mid layers onward, consistent with model-specific memory retrieval, while math reasoning shows no consistent advantage at any depth.
Read the full abstract

All authors Tomer Ashuach, Shai Gretz, Yoav Katz, Yonatan Belinkov, Liat Ein-Dor

Computation and Language · Cross-listed from cs.CR

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors

Rui Yin, Tianxu Han, Naen Xu et al. (+8 more)

Safety-aligned large language models (LLMs) are increasingly deployed in real-world pipelines, yet this deployment also enlarges the supply-chain attack surface: adversaries can distribute backdoored checkpoints that behave normally under standard evaluation but jailbreak when a hidden trigger is present. Recent post-hoc weight-editing methods offer an efficient approach to injecting such backdoors by directly modifying model weights to map a trigger to an attacker-specified response. However, existing methods typically optimize a token-level mapping that forces an affirmative prefix (e.g., “Sure”), which does not guarantee sustained harmful output – the model may begin with apparent agreement yet revert to safety-aligned refusal within a few decoding steps. We address this reliability gap by shifting the backdoor objective from surface tokens to internal representations. We extract a steering vector that captures the difference between compliant and refusal behaviors, and compile it into a persistent weight modification that activates only when the trigger is present. To preserve stealthiness and benign utility, we impose a null-space constraint so that the injected edit remains dormant on clean inputs. The method is efficient, requiring only a small set of examples and admitting a closed-form solution. Across multiple safety-aligned LLMs and jailbreak benchmarks, our method achieves high triggered attack success while maintaining non-triggered safety and general utility.
Read the full abstract

All authors Rui Yin, Tianxu Han, Naen Xu, Changjiang Li, Ping He, Chunyi Zhou, Jun Wang, Zhihui Fu, Tianyu Du, Jinbao Li, Shouling Ji

Computation and Language · Cross-listed from cs.AI

MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents

Joongmin Shin, Chanjun Park, Jeongbae Park et al. (+2 more)

RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect complex and long industrial document structures, causing information loss and reduced answer quality. To address this, we introduce MultiDocFusion, a multimodal chunking pipeline that integrates: (i) detection of document regions using vision-based document parsing, (ii) text extraction from these regions via OCR, (iii) reconstruction of document structure into a hierarchical tree using large language model (LLM)-based document section hierarchical parsing (DSHP-LLM), and (iv) construction of hierarchical chunks through DFS-based grouping. Extensive experiments across industrial benchmarks demonstrate that MultiDocFusion improves retrieval precision by 8-15% and ANLS QA scores by 2-3% compared to baselines, emphasizing the critical role of explicitly leveraging document hierarchy for multimodal document-based QA. These significant performance gains underscore the necessity of structure-aware chunking in enhancing the fidelity of RAG-based QA systems.
Read the full abstract

All authors Joongmin Shin, Chanjun Park, Jeongbae Park, Jaehyung Seo, Heuiseok Lim

Computation and Language

ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection

Boyang Li, Hongzhe Shou, Yuanyuan Liang et al. (+2 more)

Existing Chinese toxic content detection methods mainly target sentence-level classification but often fail to provide readable and contiguous toxic evidence spans. We propose ToxiTrace, an explainability-oriented method for BERT-style encoders with three components: (1) CuSA, which refines encoder-derived saliency cues into fine-grained toxic spans with lightweight LLM guidance; (2) GCLoss, a gradient-constrained objective that concentrates token-level saliency on toxic evidence while suppressing irrelevant activations; and (3) ARCL, which constructs sample-specific contrastive reasoning pairs to sharpen the semantic boundary between toxic and non-toxic content. Experiments show that ToxiTrace improves classification accuracy and toxic span extraction while preserving efficient encoder-based inference and producing more coherent, human-readable explanations. We have released the model at https://huggingface.co/ArdLi/ToxiTrace.
Read the full abstract

All authors Boyang Li, Hongzhe Shou, Yuanyuan Liang, Jingbin Zhang, Fang Zhou

Computation and Language

CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems

Jingbo Yang, Guanyu Yao, Bairu Hou et al. (+5 more)

As Large Language Models (LLMs) are increasingly deployed as task-oriented agents in enterprise environments, ensuring their strict adherence to complex, domain-specific operational guidelines is critical. While utilizing an LLM-as-a-Judge is a promising solution for scalable evaluation, the reliability of these judges in detecting specific policy violations remains largely unexplored. This gap is primarily due to the lack of a systematic data generation method, which has been hindered by the extensive cost of fine-grained human annotation and the difficulty of synthesizing realistic agent violations. In this paper, we introduce CompliBench, a novel benchmark designed to evaluate the ability of LLM judges to detect and localize guideline violations in multi-turn dialogues. To overcome data scarcity, we develop a scalable, automated data generation pipeline that simulates user-agent interactions. Our controllable flaw injection process automatically yields precise ground-truth labels for the violated guideline and the exact conversation turn, while an adversarial search method ensures these introduced perturbations are highly challenging. Our comprehensive evaluation reveals that current state-of-the-art proprietary LLMs struggle significantly with this task. In addition, we demonstrate that a small-scale judge model fine-tuned on our synthesized data outperforms leading LLMs and generalizes well to unseen business domains, highlighting our pipeline as an effective foundation for training robust generative reward models.
Read the full abstract

All authors Jingbo Yang, Guanyu Yao, Bairu Hou, Xinghan Yang, Nikolai Glushnev, Iwona Bialynicka-Birula, Duo Ding, Shiyu Chang

Computation and Language

ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance

Haoran Li, Yulin Chen, Huihao Jing et al. (+6 more)

Individuals' concerns about data privacy and AI safety are highly contextualized and extend beyond sensitive patterns. Addressing these issues requires reasoning about the context to identify and mitigate potential risks. Though researchers have widely explored using large language models (LLMs) as evaluators for contextualized safety and privacy assessments, these efforts typically assume the availability of complete and clear context, whereas real-world contexts tend to be ambiguous and incomplete. In this paper, we propose ContextLens, a semi-rule-based framework that leverages LLMs to ground the input context in the legal domain and explicitly identify both known and unknown factors for legal compliance. Instead of directly assessing safety outcomes, our ContextLens instructs LLMs to answer a set of crafted questions that span over applicability, general principles and detailed provisions to assess compliance with pre-defined priorities and rules. We conduct extensive experiments on existing compliance benchmarks that cover the General Data Protection Regulation (GDPR) and the EU AI Act. The results suggest that our ContextLens can significantly improve LLMs' compliance assessment and surpass existing baselines without any training. Additionally, our ContextLens can further identify the ambiguous and missing factors.
Read the full abstract

All authors Haoran Li, Yulin Chen, Huihao Jing, Wenbin Hu, Tsz Ho Li, Chanhou Lou, Hong Ting Tsang, Sirui Han, Yangqiu Song

Computation and Language · Cross-listed from cs.AI

Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization

Yizhe Chi, Deyao Hong, Dapeng Jiang et al. (+18 more)

Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world engineering that is often captured through the iterative optimization of feasible designs. To this end, we introduce Frontier-Eng, a human-verified benchmark for generative optimization – an iterative propose-execute-evaluate loop in which an agent generates candidate artifacts, receives executable verifier feedback, and revises them under a fixed interaction budget – spanning $47$ tasks across five broad engineering categories. Unlike previous suites, Frontier-Eng tasks are grounded in industrial-grade simulators and verifiers that provide continuous reward signals and enforce hard feasibility constraints under constrained budgets. We evaluate eight frontier language models using representative search frameworks, finding that while GPT 5.4 achieves the most robust performance, the benchmark remains challenging for all models. Our analysis suggests a dual power-law decay in improvement frequency ($\sim$ 1/iteration) and magnitude ($\sim$ 1/improvement count). We further show that although width improves parallelism and diversity, depth remains crucial for hard-won improvements under a fixed budget. Frontier-Eng establishes a new standard for assessing the capacity of AI agents to integrate domain knowledge with executable feedback to solve complex, open-ended engineering problems.
Read the full abstract

All authors Yizhe Chi, Deyao Hong, Dapeng Jiang, Tianwei Luo, Kaisen Yang, Boshi Zhang, Zhe Cao, Xiaoyan Fan, Bingxiang He, Han Hao, Weiyang Jin, Dianqiao Lei, Qingle Liu, Houde Qian, Bowen Wang, Situ Wang, Youjie Zheng, Yifan Zhou, Calvin Xiao, Eren Cai, Qinhuai Na

Computation and Language · Cross-listed from cs.CY

The Enforcement and Feasibility of Hate Speech Moderation

Manuel Tonneau, Dylan Thurgood, Diyi Liu et al. (+7 more)

Online hate speech is associated with harms ranging from deteriorating mental health to violence, yet how consistently platforms moderate hate, and whether enforcement is feasible at scale, remain poorly understood. We audit hate speech moderation on Twitter (now X) using 540,000 tweets annotated by trained native speakers, representative of a full day on the platform. Five months after posting, 80% of hateful tweets, including violent ones, remained online. Removal was only marginally more likely than for non-hateful tweets, far below scams or adult content, and insensitive to severity and reach. Automated detection could not reliably classify hate but ranked it highly, enabling human triage. Simulating this workflow, current staffing curbed little exposure, yet substantial reductions proved financially feasible, far below applicable regulatory fines. Persistent hate reflects resource allocation, not technical limits.
Read the full abstract

All authors Manuel Tonneau, Dylan Thurgood, Diyi Liu, Niyati Malhotra, Victor Orozco-Olvera, Ralph Schroeder, Scott A. Hale, Manoel Horta Ribeiro, Paul Röttger, Samuel P. Fraiberger

Computation and Language

Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning

Houxing Ren, Mingjie Zhan, Zimu Lu et al. (+4 more)

Spreadsheets are central to real-world applications such as enterprise reporting, auditing, and scientific data management. Despite their ubiquity, existing large language model based approaches typically treat tables as plain text, overlooking critical layout cues and visual semantics. Moreover, real-world spreadsheets are often massive in scale, exceeding the input length that LLMs can efficiently process. To address these challenges, we propose SpreadsheetAgent, a two-stage multi-agent framework for spreadsheet understanding that adopts a step-by-step reading and reasoning paradigm. Instead of loading the entire spreadsheet at once, SpreadsheetAgent incrementally interprets localized regions through multiple modalities, including code execution results, images, and LaTeX tables. The method first constructs a structural sketch and row/column summaries, and then performs task-driven reasoning over this intermediate representation in the Solving Stage. To further enhance reliability, we design a verification module that validates extracted structures via targeted inspections, reducing error propagation and ensuring trustworthy inputs for downstream reasoning. Extensive experiments on two spreadsheet datasets demonstrate the effectiveness of our approach. With GPT-OSS-120B, SpreadsheetAgent achieves 38.16% on Spreadsheet Bench, outperforming the ChatGPT Agent baseline (35.27%) by 2.89 absolute points. These results highlight the potential of SpreadsheetAgent to advance robust and scalable spreadsheet understanding in real-world applications. Code is available at https://github.com/renhouxing/SpreadsheetAgent.git.
Read the full abstract

All authors Houxing Ren, Mingjie Zhan, Zimu Lu, Ke Wang, Yunqiao Yang, Haotian Hou, Hongsheng Li

Computation and Language · Cross-listed from cs.SE

CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation

Zaoyu Chen, Jianbo Dai, Boyu Zhu et al. (+6 more)

Large language models (LLMs) can generate code from natural language, but the extent to which they capture intended program behavior remains unclear. Executable behavioral specifications, defined via preconditions and postconditions, provide a concrete means to assess such understanding. However, existing work on specification generation is constrained in evaluation methodology, task settings, and specification expressiveness. We introduce CodeSpecBench, a benchmark for executable behavioral specification generation under an execution-based evaluation protocol. CodeSpecBench supports both function-level and repository-level tasks and encodes specifications as executable Python functions. Constructed from diverse real-world codebases, it enables a realistic assessment of both correctness (accepting valid behaviors) and completeness (rejecting invalid behaviors). Evaluating 15 state-of-the-art LLMs on CodeSpecBench, we observe a sharp performance degradation on repository-level tasks, where the best model attains only a 20.2% pass rate. We further find that specification generation is substantially more challenging than code generation, indicating that strong coding performance does not necessarily reflect deep understanding of intended program semantics. Our data and code are available at https://github.com/SparksofAGI/CodeSpecBench.
Read the full abstract

All authors Zaoyu Chen, Jianbo Dai, Boyu Zhu, Jingdong Wang, Huiming Wang, Xin Xu, Haoyang Yuan, Zhijiang Guo, Xiao-Ming Wu

Computation and Language

CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades

Raeyoung Chang, Dongwook Kwon, Jisoo Lee et al. (+1 more)

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature escalations to costlier models or experts due to under-confidence and inefficient compute scaling. CascadeDebate addresses this gap by inserting multi-agent deliberation directly at each tier's escalation boundary. Confidence-based routers activate lightweight agent ensembles only for uncertain cases, enabling consensus-driven resolution of ambiguities internally without invoking higher-cost upgrades. Our unified architecture alternates single-model inference with selective multi-agent deliberation across model scales, culminating in human experts as the final fallback. This design scales test-time compute dynamically according to query difficulty. Across five benchmarks spanning science, medicine, and general knowledge, CascadeDebate outperforms strong single-model cascades and standalone multi-agent systems by up to 26.75 percent. An online threshold optimizer proves essential, boosting accuracy by 20.98 to 52.33 percent relative improvement over fixed policies and enabling elastic adaptation to real-world distributions.
Read the full abstract

All authors Raeyoung Chang, Dongwook Kwon, Jisoo Lee, Nikhil Verma

Computation and Language

Coding-Free and Privacy-Preserving Agentic Framework for Data-Driven Clinical Research

Taehun Kim, Hyeryun Park, Hyeonhoon Lee et al. (+3 more)

Clinical data-driven research requires clinical expertise, programming skills, access to patient data, and extensive documentation, creating barriers and slowing the pace for clinicians and external researchers. To address this, we developed the Clinical Agentic Research Intelligence System (CARIS) that automates the workflow: research planning, literature search, cohort construction, Institutional Review Board (IRB) documentation, Vibe Machine Learning (ML), and report generation, with human-in-the-loop refinement. CARIS integrates Large Language Models (LLMs) with modular tools through the Model Context Protocol (MCP), enabling natural language-driven research without coding while allowing users to access only outputs. We evaluated CARIS on three heterogeneous datasets with distinct clinical tasks, where it completed planning and IRB documentation within four iterations, supported Vibe ML, and generated reports, achieving 96% completeness in LLM-based evaluation and 82% in human evaluation. CARIS demonstrates potential to reduce documentation burden and technical barriers, accelerating data-driven clinical research across public and private data environments.
Read the full abstract

All authors Taehun Kim, Hyeryun Park, Hyeonhoon Lee, Yushin Lee, Kyungsang Kim, Hyung-Chul Lee

Computation and Language · Cross-listed from cs.AI

How memory can affect collective and cooperative behaviors in an LLM-Based Social Particle Swarm

Taisei Hishiki, Takaya Arita and Reiji Suzuki

This study examines how memory shapes the collective and cooperative dynamics of Large Language Model (LLM) agents in a multi-agent system. To this end, we extend the Social Particle Swarm (SPS) model, in which agents move in a two-dimensional space and play the Prisoner's Dilemma with neighboring agents, by replacing its rule-based agents with LLM agents endowed with Big Five personality scores and varying memory lengths. Using Gemini 2.0 Flash, we find that memory length is a critical parameter governing collective behavior: even a minimal memory drastically suppressed cooperation, transitioning the system from stable cooperative clusters through cyclical formation and collapse of clusters to a state of scattered defection as memory length increased. Big Five personality traits correlated with agent behaviors in partial agreement with findings from experiments with human participants, supporting the validity of the model. This effect of memory appeared whether or not personality was assigned. With heterogeneous personalities, individual behavior reflected the assigned traits and cooperation collapsed under long memory, whereas without personality Gemini's cooperative disposition dominated and cooperation was broadly maintained. Sentiment analysis of agents' reasoning texts showed that the model interprets memory increasingly negatively as its length grows, already in the early phase, providing a micro-level account of the suppression of cooperation. These results suggest that how an LLM interprets accumulated memory is a key driver of emergent social behavior in Generative Agent-Based Modeling.
Read the full abstract

Computation and Language

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration

Zhuofan Wen and Yang Feng

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft models but face limitations: shallow layers often produce overconfident yet incorrect token predictions, and the presence of difficult tokens in a draft sequence forces redundant computation through deeper layers, undermining both draft acceptance and overall speedup. To address these issues, we propose a novel self-draft framework that suppresses spurious confidence via layer-wise temperature annealing in early-exit decision and adaptively bounds speculation length based on token-wise decoding difficulty. By reprocessing the hidden states of draft tokens in a unified parallel pass through deep layers, our method maintains exact output equivalence with the original model while maximizing computational efficiency. It requires no modifications to the base LLM parameters and achieves up to 2.33x wall-time speedup over standard autoregressive decoding across diverse long-form generation tasks and multiple model architectures.
Read the full abstract

Computation and Language

Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature

Jinkai Tao, Yubo Wang, Xiaoyu Liu et al. (+1 more)

Identifying promising research directions in fast-moving subareas is one of the most cognitively expensive tasks in modern AI research. Existing LLM-driven scientific discovery systems are typically limited to one-shot prompting on static literature snapshots and are validated only against contemporary judges such as human reviewers, agent peer review, wet-lab assays, or self-evaluation, leaving open whether they can anticipate future trends. We present Continuous Knowledge Metabolism (CKM), an AI workflow for hypothesis generation with three key capabilities: (i) continuous literature metabolism via sliding windows that maintain an evolving knowledge state; (ii) predictive evaluation, which grades hypotheses against papers published after the generation window; and (iii) practitioner-grade failure detection that diagnoses workflow failure modes from its outputs. On a 50-topic machine learning benchmark, CKM-Lite produces at least one validated hypothesis on 72% of topics (36 out of 50), more than doubling a one-shot baseline (30%) at approximately 3 dollars per topic and achieving 91% lower token cost. Validated hypotheses precede their matched papers by an average of 404 days (55 hits across 36 topics; median 399 days, range 66-757 days). Broadly, predictive validation against future literature provides a falsifiable, low-cost alternative to contemporary-judge evaluation protocols and can be applied wherever a corpus has dated publication records.
Read the full abstract

All authors Jinkai Tao, Yubo Wang, Xiaoyu Liu, Menglin Yang

Computation and Language · Cross-listed from cs.LG

MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization

Ziqing Wang, Yibo Wen, Abhishek Pandy et al. (+2 more)

In drug discovery, molecular optimization aims to iteratively refine a lead compound to improve molecular properties while preserving structural similarity to the original molecule. However, each oracle evaluation is expensive, making sample efficiency a key challenge for existing methods under a limited oracle budget. Trial-and-error approaches require many oracle calls, while methods that leverage external knowledge tend to reuse familiar templates and struggle on challenging objectives. A key missing piece is long-term memory that can ground decisions and provide reusable insights for future optimizations. To address this, we present MolMem (Molecular optimization with Memory), a multi-turn agentic reinforcement learning (RL) framework with a dual-memory system. Specifically, MolMem uses Static Exemplar Memory to retrieve relevant exemplars for cold-start grounding, and Evolving Skill Memory to distill successful trajectories into reusable strategies. Built on this memory-augmented formulation, we train the policy with dense step-wise rewards, turning costly rollouts into long-term knowledge that improves future optimization. Extensive experiments show that MolMem achieves 90% success on single-property tasks (1.5$\times$ over the best baseline) and 52% on multi-property tasks using only 500 oracle calls. Our code is available at https://github.com/REAL-Lab-NU/MolMem.
Read the full abstract

All authors Ziqing Wang, Yibo Wen, Abhishek Pandy, Han Liu, Kaize Ding

Computation and Language

Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems

Tao Feng, Pengrui Han, Guanyu Lin et al. (+2 more)

Large language models (LLMs) have transformed AI research thanks to their powerful internal capabilities and knowledge. However, existing LLMs still fail to effectively incorporate the massive external knowledge when interacting with the world. Although retrieval-augmented LLMs are proposed to mitigate the issue, they are still fundamentally constrained by the context length of LLMs, as they can only retrieve top-K raw data chunks from the external knowledge base which often consists of millions of data chunks. Here we propose Thought-Retriever, a novel model-agnostic algorithm that helps LLMs generate output conditioned on arbitrarily long external data, without being constrained by the context length or number of retrieved data chunks. Our key insight is to let an LLM fully leverage its intermediate responses generated when solving past user queries (thoughts), filtering meaningless and redundant thoughts, organizing them in thought memory, and retrieving the relevant thoughts when addressing new queries. This effectively equips LLM-based agents with a self-evolving long-term memory that grows more capable through continuous interaction. Besides algorithmic innovation, we further meticulously prepare a novel benchmark, AcademicEval, which requires an LLM to faithfully leverage ultra-long context to answer queries based on real-world academic papers. Extensive experiments on AcademicEval and two other public datasets validate that Thought-Retriever remarkably outperforms state-of-the-art baselines, achieving an average increase of at least 7.6% in F1 score and 16% in win rate across various tasks. More importantly, we further demonstrate two exciting findings: (1) Thought-Retriever can indeed help LLM self-evolve after solving more user queries; (2) Thought-Retriever learns to leverage deeper thoughts to answer more abstract user queries.
Read the full abstract

All authors Tao Feng, Pengrui Han, Guanyu Lin, Ge Liu, Jiaxuan You

Computation and Language · Cross-listed from cs.AI

HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models

Jawad Hossain, Xiangyu Guo, Jiawei Zhou et al. (+1 more)

Small language models (SLMs) often struggle with complex mathematical reasoning due to limited capacity to maintain long chains of intermediate steps and to recover from early errors. We address this challenge by introducing a hint-assisted reasoning framework that incrementally guides SLMs through multi-step mathematical problem solving. Our approach decomposes solutions into sequential reasoning steps and provides context-aware hints, where hints are generated by a separate SLM trained via distillation from a strong large language model. While the hint-generating SLM alone is not capable of solving the problems, its collaboration with a reasoning SLM enables effective guidance, forming a cooperative two-model system for reasoning. Each hint is generated conditionally on the problem statement and the accumulated reasoning history, providing stepwise, localized guidance without revealing full solutions. This reduces error propagation and allows the reasoning model to focus on manageable subproblems. Experiments across diverse mathematical benchmarks and models demonstrate that hint assistance consistently improves reasoning accuracy for SLMs, yielding substantial gains over standard prompting while preserving model efficiency. These results highlight that structured collaboration between SLMs-via hint generation and reasoning-offers an effective and lightweight mechanism for enhancing mathematical reasoning.
Read the full abstract

All authors Jawad Hossain, Xiangyu Guo, Jiawei Zhou, Chong Liu

Computation and Language · Cross-listed from cs.AI

Designing Reliable LLM-Assisted Rubric Scoring for Constructed Responses: Evidence from Physics Exams

Xiuxiu Tang, G. Alex Ambrose and Ying Cheng

Student responses in STEM assessments are often handwritten and combine symbolic expressions, calculations, and diagrams, creating substantial variation in format and interpretation. Despite their importance for evaluating students' reasoning, such responses are time-consuming to score and prone to rater inconsistency, particularly when partial credit is required. Recent advances in large language models (LLMs) have increased attention to AI-assisted scoring, yet evidence remains limited regarding how rubric design and LLM configurations influence reliability across performance levels. This study examined the reliability of AI-assisted scoring of undergraduate physics constructed responses using GPT-4o. Twenty authentic handwritten exam responses were scored across two rounds by four instructors and by the AI model using skill-based rubrics with differing levels of analytic granularity. Prompting format and temperature settings were systematically varied. Overall, human-AI agreement on total scores was comparable to human inter-rater reliability and was highest for high- and low-performing responses, but declined for mid-level responses involving partial or ambiguous reasoning. Criterion-level analyses showed stronger alignment for clearly defined conceptual skills than for extended procedural judgments. A more fine-grained, checklist-based rubric improved consistency relative to holistic scoring. These findings indicate that reliable AI-assisted scoring depends primarily on clear, well-structured rubrics, while prompting format plays a secondary role and temperature has relatively limited impact. More broadly, the study provides transferable design recommendations for implementing reliable LLM-assisted scoring in STEM contexts through skill-based rubrics and controlled LLM settings.
Read the full abstract

Computation and Language

LLM-Guided Semantic Bootstrapping for Interpretable Text Classification with Tsetlin Machines

Jiechao Gao, Rohan Kumar Yadav, Yuangang Li et al. (+4 more)

Pretrained language models (PLMs) like BERT provide strong semantic representations but are costly and opaque, while symbolic models such as the Tsetlin Machine (TM) offer transparency but lack semantic generalization. We propose a semantic bootstrapping framework that transfers LLM knowledge into symbolic form, combining interpretability with semantic capacity. Given a class label, an LLM generates sub-intents that guide synthetic data creation through a three-stage curriculum (seed, core, enriched), expanding semantic diversity. A Non-Negated TM (NTM) learns from these examples to extract high-confidence literals as interpretable semantic cues. Injecting these cues into real data enables a TM to align clause logic with LLM-inferred semantics. Our method requires no embeddings or runtime LLM calls, yet equips symbolic models with pretrained semantic priors. Across multiple text classification tasks, it improves interpretability and accuracy over vanilla TM, achieving performance comparable to BERT while remaining fully symbolic and efficient.
Read the full abstract

All authors Jiechao Gao, Rohan Kumar Yadav, Yuangang Li, Yuandong Pan, Jie Wang, Ying Liu, Michael Lepech

Computation and Language · Cross-listed from cs.CR

TimeMark: A Trustworthy Time Watermarking Framework for Exact Generation-Time Recovery from AIGC

Shangkun Che, Silin Du and Ge Gao

The widespread use of Large Language Models (LLMs) in text generation has raised increasing concerns about intellectual property disputes. Watermarking techniques, which embed meta information into AI-generated content (AIGC), have the potential to serve as judicial evidence. However, existing methods rely on statistical signals in token distributions, leading to inherently probabilistic detection and reduced reliability, especially in multi-bit encoding (e.g., timestamps). Moreover, such methods introduce detectable statistical patterns, making them vulnerable to forgery attacks and enabling model providers to fabricate arbitrary watermarks. To address these issues, we propose the concept of trustworthy watermark, which achieves reliable recovery with 100% identification accuracy while resisting both user-side statistical attacks and provider-side forgery. We focus on trustworthy time watermarking for use as judicial evidence. Our framework integrates cryptographic techniques and encodes time information into time-dependent secret keys under regulatory supervision, preventing arbitrary timestamp fabrication. The watermark payload is decoupled from time and generated as a random, non-stored bit sequence for each instance, eliminating statistical patterns. To ensure verifiability, we design a two-stage encoding mechanism, which, combined with error-correcting codes, enables reliable recovery of generation time with theoretically perfect accuracy. Both theoretical analysis and experiments demonstrate that our framework satisfies the reliability requirements for judicial evidence and offers a practical solution for future AIGC-related intellectual property disputes.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering

Weikang Zhang, Zimo Zhu, Zhichuan Yang et al. (+3 more)

Simulating Standardized Patients with cognitive impairment offers a scalable and ethical solution for clinical training. However, existing methods rely on discrete prompt engineering and fail to capture the heterogeneity of deficits across varying domains and severity levels. To address this limitation, we propose StsPatient for the fine-grained simulation of cognitively impaired patients. We innovatively capture domain-specific features by extracting steering vectors from contrastive pairs of instructions and responses. Furthermore, we introduce a Stochastic Token Modulation (STM) mechanism to regulate the intervention probability. STM enables precise control over impairment severity while mitigating the instability of conventional vector methods. Comprehensive experiments demonstrate that StsPatient significantly outperforms baselines in both clinical authenticity and severity controllability.
Read the full abstract

All authors Weikang Zhang, Zimo Zhu, Zhichuan Yang, Chen Huang, Wenqiang Lei, See-Kiong Ng

Computation and Language

Efficient Best-Of-N with Radial Consensus Score

Manh Nguyen, Sunil Gupta and Hung Le

Solving complex problems with large language models (LLMs) often requires selecting the best answer from multiple candidate responses (best-of-$N$), yet identifying the most reliable one remains challenging, particularly when correctness does not align with majority agreement. Existing approaches based on voting or probability scoring rely on surface-level signals (e.g., frequency or token-level likelihood), often missing high-quality rare answers and ignoring the geometric structure of candidate representations, where correctness may emerge as semantic consistency rather than surface agreement. To address these limitations, we introduce Radial Consensus Score (RCS), a simple, efficient, and training-free method for best-of-$N$ selection. RCS models semantic consensus by computing a weighted Frechet mean (semantic center) of answer embeddings and ranking candidates by their radial distance to this center. This enables it to recover semantically coherent correct answers despite lexical fragmentation, even when no single surface form holds a plurality under exact-match voting. Importantly, RCS offers a flexible framework that supports multiple weighting schemes, enabling the integration of arbitrary signals, such as semantic agreement or model confidence, with the position of the center adapting accordingly. Extensive experiments across five open-weight models and various benchmarks demonstrate that RCS matches or outperforms strong baselines at every sampling budget, with the largest gains when correct answers are lexically fragmented. Moreover, RCS serves as an effective drop-in replacement for majority voting in multi-agent debate and remains effective in black-box scenarios. These results suggest that geometric consensus can serve as a scalable and reliable alternative to voting-based methods for answer selection. Code is publicly available at https://github.com/manhitv/RCS.
Read the full abstract