Peer Revenue Now accepting positions

Papers

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

Computer Science Computation and Language

cs.CL Watch Computation and Language

Monday 18 May

Computation and Language

Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction

Luu Huu Phuc, Ratan Bahadur Thapa, Mojtaba Nayyeri et al. (+3 more)

We introduce Graph-Augmented Sequence-to-Sequence (GA-S2S), a novel framework that integrates a T5-small encoder-decoder with a Relational Graph Attention Network (RGAT) to improve link prediction in knowledge graphs. While existing Seq2Seq models rely solely on surface-level textual descriptions of entities and relations and at best, flatten the neighborhoods of a query entity into a single linear sequence, thereby discarding the inherent graph structure, GA-S2S jointly encodes both textual features and the full $k$-hop subgraph topology surrounding the query entity. By integrating raw encoder outputs with RGAT's relation-aware embeddings, our model captures and leverages richer multi-hop relational patterns and textual information. Our preliminary experiments on the CoDEx dataset demonstrate that GA-S2S outperforms competitive Seq2Seq-based baseline models, achieving up to a 19% relative gain in link prediction accuracy.
Read the full abstract

All authors Luu Huu Phuc, Ratan Bahadur Thapa, Mojtaba Nayyeri, Jingcheng Wu, Evgeny Kharlamov, Steffen Staab

Computation and Language · Cross-listed from cs.AI

Scalable Environments Drive Generalizable Agents

Jiayi Zhang, Fanqi Kong, Guibin Zhang et al. (+7 more)

Generalizable agents should adapt to diverse tasks and unseen environments beyond their training distribution. This position paper argues that such generalization requires environment scaling: expanding the distribution of executable rule-sets that agents interact with, rather than only increasing trajectories or tasks within fixed benchmarks. Current scaling practices largely focus on collecting more experience or broader task sets under fixed interaction rules, leaving agents brittle when underlying interfaces, dynamics, observations, or feedback signals change. The core challenge is therefore a world-level distribution shift: agents need systematic exposure to environments with meaningfully different executable rule-sets. To clarify this challenge, we propose a unified taxonomy that separates trajectory scaling, task scaling, and environment scaling by their primary deliverables and by what changes in the executable rule-set. Building on this taxonomy, we synthesize construction paradigms for scalable environments, contrasting programmatic generators that prioritize controllability and verifiability with generative world models that offer broader coverage and open-endedness. We further outline how environment scaling can be coupled with stateful learning mechanisms, emphasizing learned update rules for cross-environment adaptation. We conclude by discussing alternative perspectives and argue that scalable environments provide the essential substrate for measurable and controllable progress toward robust general agents.
Read the full abstract

All authors Jiayi Zhang, Fanqi Kong, Guibin Zhang, Maojia Song, Zhaoyang Yu, Jianhao Ruan, Jinyu Xiang, Bang Liu, Chenglin Wu, Yuyu Luo

Computation and Language · Cross-listed from cs.AI

TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction

Tej Sanibh Ranade

Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor uniformly less trustworthy. Yet hallucination reduction is usually instantiated through one fixed intervention form: contrast one layer against another, steer along a truthfulness direction, or defer to external evidence. This framing is structurally incomplete. Cross-layer factual evidence does not evolve uniformly: in some failures truthful support is present internally and later suppressed, whereas in others candidate competition remains genuinely multi-directional across depth, so no single signed scalar family is generally sufficient. We introduce Trajectory Correction from Cross-layer Evidence for Hallucination Reduction (TRACE), a deterministic, training-free algorithm which corrects hallucinations at inference time by deriving both the corrective layer and the appropriate correction operator from each input's cross-layer candidate trajectory inside the LLM's own forward pass. Under one frozen hyperparameter setting, TRACE selects among scalar reversal, earlier-state recovery, and candidate-space correction using only model-internal evidence. Evaluated as a single universal algorithm across 15 models, 8 model families, and 3 factuality benchmarks, TRACE improves every evaluation cell, yielding mean gains of +12.26 MC1 points and +8.65 MC2-style points with no regressions, with gains reaching +47.20 MC1 and +43.38 MC2-style points. The method uses no labels, retrieval, pretraining, finetuning, or per-model calibration.
Read the full abstract

Computation and Language

FOL2NS: Generating Natural Sentences from First-Order Logic

Mei Jia

Translating formal language into natural language is a foundational challenge in NLP, driving various downstream applications in semantic parsing, theorem validation, and question answering. In this study, we introduce First-Order Logic to Natural Sentence (FOL2NS), a neurosymbolic framework designed to generate synthetic FOL formulas and convert them into natural human expressions. It handles deeply nested structures with varying quantifier depths (QD), which are rarely captured by existing corpora. By combining rule-driven modules with fine-tuned language models, FOL2NS enhances the diversity and coverage of the generated samples. In our experiments, we systematically evaluate the framework's capabilities through both character-level analysis and overall performance metrics. Experimental results show that FOL2NS can reliably produce well-formed templates and fluent statements, but it faces challenges in achieving precise semantic representations and natural generation as structural complexity increases.
Read the full abstract

Computation and Language

iPOE: Interpretable Prompt Optimization via Explanations

Jiahui Li, Yarik Menchaca Resendiz, Sean Papay et al. (+1 more)

Prompt optimization has often been framed as a discrete search problem to find high-performing and robust instructions for a large language model (LLM). However, the search result might not make it transparent why and where specific prompt changes lead to performance gains. This is in contrast to how humans are instructed for annotation tasks. Here, researchers carefully design annotation guidelines, leading to enhanced annotation consistency. Our paper aims at joining these two approaches and introduces iPOE, a novel interpretable prompt optimization strategy via explanations. We guide the prompt optimization process by automatically created guidelines from explanations of annotation decisions (either automatically generated or from humans). This set of guidelines is furthermore optimized by a series of operations, including removing, adding, shuffling, and merging. The resulting prompt includes guidelines that instruct the annotation, making the decision process of the LLM and the optimization transparent. It therefore supports also laypeople in prompt optimization. In our experiments on four datasets, we find that iPOE can improve over the evaluated baselines by up to 39% and LLM explanations can replace human explanations in the proposed method. Moreover, our interpretability validation study demonstrates that humans and LLMs substantially agree on which guidelines contribute to their annotations, achieving a Cohen's kappa score between annotators and LLMs of up to 0.68, 0.80, and 0.95 for the emotion classification, medical fact-checking, and hate speech detection tasks respectively.
Read the full abstract

All authors Jiahui Li, Yarik Menchaca Resendiz, Sean Papay, Roman Klinger

Computation and Language

How Good LLMs Are at Answering Bangla Medical Visual Questions? Dataset and Benchmarking

Rafid Ahmed, Intesar Tahmid, Mir Sazzat Hossain et al. (+3 more)

Recent advancements in Large Language Models (LLMs) and Large Vision Language Models (LVLMs) have enabled general-purpose systems to demonstrate promising capabilities in complex reasoning tasks, including those in the medical domain. Medical Visual Question Answering (MedVQA) has particularly benefited from these developments. However, despite Bangla being one of the most widely spoken languages globally, there exists no established MedVQA benchmark for it. To address this gap, we introduce BanglaMedVQA, a dataset comprising clinically validated image-question-answer pairs, along with a comprehensive evaluation of current foundation models on this resource. Consistent with prior findings that report low performance of current models on English MedVQA benchmarks, our analysis reveals that Bangla performance is substantially lower, reflecting the challenges inherent to low-resource languages. Even top-performing models such as Gemini and GPT-4.1 mini fail to accurately answer specialized diagnostic questions, indicating severe limitations in fine-grained medical reasoning. Although certain open-source models, such as Gemma-3, occasionally outperform these models in general categories, they too struggle with clinically complex questions, underscoring the urgent need for top-notch evaluation method.
Read the full abstract

All authors Rafid Ahmed, Intesar Tahmid, Mir Sazzat Hossain, Tasnimul Hossain Tomal, Md Fahim, Md Farhad Alam Bhuiyan

Computation and Language

How Loud Rumbles Hit Newsstands: A Data Analysis of Coverage and Spatial Bias in German News about Landslides Around the World

Brielen Madureira, Andreas Niekler, Marc Keuschnigg et al. (+1 more)

Landslides often hit newsstands due to their destructive and potentially fatal effects. News are a valuable source of information for creating or enriching disaster databases and for expediting media-based studies of the dynamics of media attention. To accomplish that, news datasets must be filtered, geolocated and validated. This paper focuses on how landslides around the world are reported in German newspapers. We analyse almost 55k news articles about 4.5k news events in a 25-year period, compare it with external measures of countries' susceptibility to landslides and provide insights, e.g. the overreporting of Southern and Western Europe, to foster further studies on inequalities in media attention to international disasters.
Read the full abstract

All authors Brielen Madureira, Andreas Niekler, Marc Keuschnigg, Mariana Madruga de Brito

Computation and Language

A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM$\Delta$ Integration into Upcycled MoE

Hao Zhou, Tianhao Li, Zhijun Wang et al. (+6 more)

Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a multilingual CPT-enhanced model with its instruct counterpart, they are plagued by a critical trade-off: mitigating parameter conflicts to preserve original abilities inevitably dilutes new language acquisition, and vice-versa. To resolve this conflict, we introduce \method, which upcycles a dense model into a Mixture-of-Experts~(MoE) architecture, allocating different experts to different languages. Alignment ability is then transferred by grafting a MoE-expanded parameter delta~($\Delta_{\text{post}}$) to the CPT-enhanced base model, bypassing the complex alignment phase. Experiments demonstrate \method's superiority even against baselines with similar FLOPs or number of parameters; it improves performance on expanded languages while effectively preserving original capabilities. We further show our approach is highly applicable across different models and Post-training deltas.
Read the full abstract

All authors Hao Zhou, Tianhao Li, Zhijun Wang, Shuaijie She, Linjuan Wu, Hao-Ran Wei, Baosong Yang, Jiajun Chen, Shujian Huang

Computation and Language · Cross-listed from cs.LG

The Expressive Power of Low Precision Softmax Transformers with (Summarized) Chain-of-Thought

Moritz Brösamle and Stephan Eckstein

Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice. We bridge this gap by analyzing standard transformer decoders with softmax attention and rounding of activations and attention weights, while allowing depth and width to grow logarithmically with the context length. As an intermediate step, we construct hardmax transformers with ternary activations and well-separated attention scores that simulate Turing machines using Chain-of-Thought (CoT). This lets us convert the constructions to equivalent softmax transformers without the unrealistic parameter magnitudes or activation precision that prior approaches would require. Using the same technique, we analyze a recently proposed summarized CoT paradigm and show that it simulates Turing machines more efficiently, with model size scaling logarithmically in a space bound rather than a time bound. We empirically test predictions made by our results on a Sudoku reasoning task and find better alignment with learnability than for prior high-precision results. Our code is available at https://github.com/moritzbroe/transformer-expressivity.
Read the full abstract

Computation and Language

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference

Jian Lin, Jiazhi Mi, Zicong Hong et al. (+5 more)

Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the full cache in host memory and selectively fetch critical entries during decoding, but this strategy quickly hits a ceiling: sparsity cannot be pushed further without degrading accuracy. As a result, when context length and batch size grow, the volume of KV transfers rises sharply and becomes the dominant source of decoding latency. We present KVDrive, a holistic multi-tier KV cache management system spanning GPU memory, host DRAM, and SSD. Unlike prior work that pursues greater sparsity through algorithmic refinements, KVDrive tackles the problem from a systems perspective - jointly orchestrating cache placement, pipeline scheduling, and cross-tier coordination to sustain high-throughput inference under tight GPU budgets. KVDrive advances three fundamental capabilities: it adapts cache management to attention behavior to maximize reuse and minimize redundant data movement; it restructures the decoding pipeline to overlap I/O- and CPU/GPU compute-bound stages, eliminating stalls across heterogeneous resources; and it harmonizes data movement across memory tiers to unlock scalable long-context inference far beyond GPU and DRAM limits. We have implemented a fully functional prototype of KVDrive and evaluated it on long-context benchmarks with popular LLMs. The system achieves up to 1.74x higher throughput compared to state-of-the-art works while preserving accuracy.
Read the full abstract

All authors Jian Lin, Jiazhi Mi, Zicong Hong, Haodong Wang, Qianli Liu, Haodyue Zhang, Peng Li, Song Guo

Computation and Language

PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence

Zile Wang, Qianli Liu, Kaibin Guo et al. (+4 more)

Deploying large language model (LLM) on edge device enables personalized LLM agents for various users. The growing availability of diverse personalized agents presents a unique opportunity for peer-to-peer (P2P) collaboration, wherein each user can delegate tasks beyond the local agent's expertise to remote agents more suited for the specific query. This paper introduces PPAI, the first personalized LLM agent interoperability system, which enables users to collaborate with each other based on agent specialization. However, the ever-changing pool of agents and their interchangeable capacity introduce new challenges when it comes to matching queries to agents and balancing loads, compared with existing P2P systems. Therefore, we propose a scalable query-agent pair scoring mechanism based on prototypes to identify suitable agents within a P2P network with churn. Moreover, we propose a multi-agent interoperability Bayesian game to balance local demand and global efficiency, when changes in remote agent load occur too quickly to be observed. Finally, we implement a prototype of PPAI and demonstrate that it substantially broadens the range of tasks that could be carried out while maintaining load balance. On average, it achieves an accuracy improvement of up to 7.96% across multiple tasks, while reducing latency by 16.34% compared to the baseline.
Read the full abstract

All authors Zile Wang, Qianli Liu, Kaibin Guo, Haodong Wang, Jian Lin, Zicong Hong, Song Guo

Computation and Language · Cross-listed from cs.LG

Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction

Gabriel Garcia

We study KV cache eviction under a shared globally capped decode-time harness. Seven policies (LRU, H2O, SnapKV, StreamingLLM, Ada-KV, QUEST, Random) share a prompt-boundary vulnerability: without structural protection, they collapse to near-zero quality on six pure-transformer models (F1$\leq$0.064). Reserving 10% of cache at each boundary recovers 69–90% of the $C{=}2{,}048$ reference-ceiling quality on seven LongBench models at $C{=}256$ (13% retention); a ten-model panel spans 68–98%. An attention-mass pilot (Qwen2.5-3B, $N{=}30$) suggests why: the position-0 sink holds ${\sim}75\%$ of prefix mass, while other boundary tokens sit near ${\sim}0.41{\times}$ uniform expectation, so attention scorers retain the sink but still drop structurally critical tokens. With protection, simplified score-isolation variants are TOST-equivalent to LRU at $K{=}32$ ($\Delta{=}0.02$); at $K{=}8$, attention policies pairwise converge yet beat LRU by 0.011–0.021 F1 across $C{=}256$ and $C{=}512$. Faithful Ada-KV/QUEST add ${\sim}0.03$–$0.04$ F1 on Mistral-7B and Phi-3.5 beyond simplified variants. A NIAH-32K regime-transfer pilot on Qwen3-4B (decode vs.\ prefill, $C{\in}\{512,2048\}$) shows near-identical protection lifts (ratio 0.99–1.00). At 64K, protection helps but recovery is modest; faithful per-head scoring matches full-cache ceiling on Gemma-3-4B at 6.3% retention only when the model already supports strong 64K retrieval without eviction. Overall: protection dominates; scoring differences are secondary once boundaries are guarded; per-head allocation gives a further modest gain.
Read the full abstract

Computation and Language

PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows

Kazuki Kawamura, Satoshi Waki and Kei Tateno

Multi-agent LLM workflows – systems composed of multiple role-specific LLM calls – often outperform single-prompt baselines, but they remain difficult to debug and refine. Failures can originate from subtle errors in intermediate outputs that propagate to downstream nodes, requiring developers to inspect long traces and infer which agent to modify. We present PROTEA, a unified interface for offline, test-driven improvement of multi-agent workflows. PROTEA executes a workflow, scores intermediate node outputs with configurable rubrics, and overlays per-node states and rationales on the workflow graph to localize likely bottlenecks. To support complex systems where final-answer references are the primary supervision, PROTEA performs backward node evaluation: it generates candidate node-level expectations from final-answer references and graph context, then compares them with observed node outputs. For selected nodes, PROTEA presents targeted prompt revisions as editable before/after comparisons, then automatically reruns and re-evaluates the workflow to show output changes and score trajectories within the same interface. In two production-adjacent workflows, PROTEA improved document-inspection accuracy from 64.3% to 83.9% and recommendation Hit@5 from 0.30 to 0.38. In a formative study with six experienced LLM developers, participants valued graph-level localization, per-node rationales, and editable before/after prompt revisions.
Read the full abstract

Computation and Language

Semantic Reranking at Inference Time for Hard Examples in Rhetorical Role Labeling

Anas Belfathi, Nicolas Hernandez, Laura Monceaux et al. (+2 more)

Rhetorical Role Labeling (RRL) assigns a functional role to each sentence in a document and is widely used in legal, medical, and scientific domains. While language models (LMs) achieve strong average performance, they remain unreliable on hard examples, where prediction confidence is low. Existing approaches typically handle uncertainty implicitly and treat labels as discrete identifiers, overlooking the semantic information encoded in label names. We introduce RISE, an inference-time semantic reranking framework that leverages label semantics to refine predictions on hard instances. RISE automatically identifies low-confidence predictions and reranks model outputs using contrastively learned label representations, without retraining or modifying the underlying model. Experiments on eight domain-specific RRL datasets with seven LMs, including encoder-based and causal architectures, show an average gain of +9.15 macro-F1 points on hard examples. For explainability, we further propose manual hardness annotations to study difficulty from both model and human perspectives, revealing a moderate agreement with Cohen's kappa = 0.40.
Read the full abstract

All authors Anas Belfathi, Nicolas Hernandez, Laura Monceaux, Warren Bonnard, Richard Dufour

Computation and Language

Bridging the Gap: Converting Read Text to Conversational Dialogue

Parshav Singla, Agnik Banerjee, Aaditya Arora et al. (+5 more)

In recent advancements within speech processing, converting read speech to conversational speech has gained significant attention. The primary challenge in this domain is maintaining naturalness and intelligibility while minimizing computational overhead for real-time applications. Traditional read speech often lacks the nuanced prosodic variation essential for natural conversational interactions, posing challenges for applications in virtual assistants, customer service, and language learning tools. This paper introduces a novel approach, Prosodic Adjustment with Conversational Context (PACC), aimed at converting read speech into natural conversational speech used in various modern applications. PACC utilizes advanced deep neural networks to analyze and modify prosodic features such as intonation, stress, and rhythm. Unlike conventional methods, our approach uses High-Fidelity Generative Adversarial Networks (HiFi-GAN) for speech synthesis. Our experimental results demonstrate significant improvements in speech conversion, enhancing naturalness and achieving better model accuracy with additional training on speech datasets. This research establishes new benchmarks in speech conversion tasks and Mean Opinion Score (MOS) evaluation for testing model accuracy, and we show that our approach can be successfully extended to other speech conversion applications.
Read the full abstract

All authors Parshav Singla, Agnik Banerjee, Aaditya Arora, Shruti Aggarwal, Anil Kumar Verma, Vikram C M, Raj Prakash Gohil, Gopal Kumar Agarwal

Computation and Language

Predictive Prefetching for Retrieval-Augmented Generation

Wuyang Zhang and Shichao Pei

Retrieval-Augmented Generation (RAG) improves factual grounding in large language models but suffers from substantial latency due to synchronous retrieval. While recent work explores asynchronous retrieval, existing approaches rely on heuristic coordination between retrieval and generation and assume stable information demands during decoding that often break in complex, multi-domain settings. In this paper, we propose an advanced asynchronous retrieval framework that enables predictive prefetching aligned with evolving information needs. The framework explicitly predicts when retrieval should be triggered and what information should be retrieved using three components, a retrieval predictor, a context monitor, and a query generator, by exploiting semantic precursors in generation dynamics that emerge several tokens before uncertainty becomes critical. Experiments on multiple benchmarks demonstrate up to 43.5% end-to-end latency reduction and 62.4% improvement in time-to-first-token, while maintaining answer quality comparable to synchronous RAG baselines.
Read the full abstract

Computation and Language

AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code

Shangzhan Li, Xinyu Yin, Xuanyu Jin et al. (+8 more)

Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resort to explicit vectorization using intrinsics, as compiler-based auto-vectorization frequently yields suboptimal results due to conservative static analysis. While Large Language Models (LLMs) have demonstrated remarkable proficiency in general code generation, they struggle with explicit vectorization due to the scarcity of high-quality corpora and the strict semantic constraints of low-level hardware instructions. In this paper, we propose AutoVecCoder, a novel framework designed to empower LLMs with the capability of automated explicit vectorization. AutoVecCoder integrates two core components: VecPrompt, an automated data synthesis pipeline to inject domain-specific intrinsic knowledge; and VecRL, a reinforcement learning framework that aligns code generation with execution efficiency. AutoVecCoder-8B trained by this framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench and, in some cases, generates implementations surpassing standard -O3 optimizations, effectively overcoming the inherent bottlenecks of traditional automated vectorization.
Read the full abstract

All authors Shangzhan Li, Xinyu Yin, Xuanyu Jin, Ye He, Yuxin Zhou, Yuxuan Li, Xu Han, Wanxiang Che, Qi Shi, Ting Liu, Maosong Sun

Computation and Language

BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting

Zhensheng Wang, Wenmian Yang, Qingtai Wu et al. (+3 more)

Quantitative backtesting is essential for evaluating trading strategies but remains hampered by high technical barriers and limited scalability. While Large Language Models (LLMs) offer a transformative path to automate this complex, interdisciplinary workflow through advanced code generation, tool usage, and agentic planning, the practical realization is significantly challenged by the current lack of a large-scale benchmark dedicated to automated quantitative backtesting, which hinders progress in this field. To bridge this critical gap, we introduce BacktestBench, the first large-scale benchmark for automated quantitative backtesting. Built from over 6 million real market records, it comprises 18,246 meticulously annotated question-answering pairs across four task categories: metrics calculation, ticker selection, strategy selection, and parameter confirmation. We also propose AutoBacktest, a robust multi-agent baseline that translates natural language strategies into reproducible backtests by coordinating a Summarizer for semantic factor extraction, a Retriever for validated SQL generation, and a Coder for Python backtesting implementation. Our evaluation on 23 mainstream LLMs, complemented by targeted ablations, identifies key factors that influence end-to-end performance and highlights the importance of grounded verification and standardized indicator representations.
Read the full abstract

All authors Zhensheng Wang, Wenmian Yang, Qingtai Wu, Lequan Ma, Yiquan Zhang, Weijia Jia

Computation and Language

Universal Adversarial Triggers

Benedict Florance Arockiaraj, Alexander Feng, Jianxiong Cai et al. (+1 more)

Recent works have illustrated that modern NLP models trained for diverse tasks ranging from sentiment analysis to language generation succumb to universal adversarial attacks, a class of input-agnostic attacks where a common trigger sequence is used to attack the model. Although these attacks are successful, the triggers generated by such attacks are ungrammatical and unnatural. Our work proposes a novel technique combining parts-of-speech filtering and perplexity based loss function to generate sensible triggers that are closer to natural phrases. For the task of sentiment analysis on the SST dataset, the method produces sensible triggers that achieve accuracies as low as 0.04 and 0.12 for flipping positive to negative predictions and vice-versa. To build robust models, we also perform adversarial training using the generated triggers that increases the accuracy of the model from 0.12 to 0.48. We aim to illustrate that adversarial attacks can be made difficult to detect by generating sensible triggers, and to facilitate robust model development through relevant defenses.
Read the full abstract

All authors Benedict Florance Arockiaraj, Alexander Feng, Jianxiong Cai, Xiaoyu Cheng

Computation and Language

Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA

Sterling Huang, Abigayle Brown, Jiyoo Noh et al. (+4 more)

Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus mainly on autoregressive architectures. This study examines whether LLMLingua-2 transfers effectively to diffusion large language models (DLLMs), specifically LLaDA-8B-Instruct. We evaluate GSM8K, DUC2004, and ShareGPT using 250 prompts per dataset at an approximate 50% compression ratio, covering mathematical reasoning, prompt reconstruction, and summarization. Outputs from original, compressed, and reconstructed prompts are compared using exact-match accuracy, BLEU, ROUGE, and BERTScore. Results show that high semantic preservation does not necessarily ensure stable downstream behavior in diffusion models. Summarization remains relatively robust, while mathematical reasoning degrades substantially despite high semantic similarity. Reconstruction further shows that semantically similar prompts may omit reasoning-critical information needed for stable denoising. Overall, compression failures are mainly driven by information omission rather than semantic drift, suggesting that autoregressive prompt compression methods may not transfer uniformly to DLLMs. These findings motivate diffusion-aware compression strategies.
Read the full abstract

All authors Sterling Huang, Abigayle Brown, Jiyoo Noh, Jiakang Xu, Wantong Huo, Kaung Myat Kyaw, Jonathan Chan

Computation and Language

A Pilot Benchmark for NL-to-FOL Translation in Planetary Exploration

Hayden Moore, Suman Saha and Mahfuza Farooque

Future planetary exploration envisions autonomous robotic agents operating under severe communication constraints, without global positioning, and with minimal human intervention. In such environments, agents must not only perceive and act, but also reason over mission objectives, operational constraints, and evolving environmental conditions. While prior work has largely focused on perception and control, the translation of high-level mission knowledge into structured, machine-interpretable representations remains underexplored. We introduce a pilot benchmark for translating natural language (NL) into First-Order Logic (FOL) within the domain of planetary exploration. The dataset is constructed from real mission documentation sourced from NASA's Planetary Data System (PDS), spanning missions from 2003 to 2013. These documents describe mission phases such as launch, boost, coast, cruise, and orbital operations in rich natural language. We manually annotate these documents with corresponding FOL representations that capture temporal structure, agent roles, and operational dependencies. In addition, we provide structured predicate vocabularies and typed constants to enable controlled experimentation with varying levels of prior knowledge. This pilot benchmark provides a foundation for research at the intersection of language understanding and formal reasoning, grounded in real-world, safety-critical mission data. The dataset is provided at: https://github.com/HaydenMM/planetary-logic-benchmark/blob/main/pilot_benchmark.json
Read the full abstract

Computation and Language · Cross-listed from cs.AI

Agentic Chunking and Bayesian De-chunking of AI Generated Fuzzy Cognitive Maps: A Model of the Thucydides Trap

Akash Kumar Panda, Olaoluwa Adigun and Bart Kosko

We automatically generate feedback causal fuzzy cognitive maps (FCMs) from text by teaching large-language-model agents to break the text into overlapping chunks of text. Convex mixing of these chunk FCMs gives a representative cyclic FCM knowledge graph. The text chunks can have different levels of overlap. The chunk FCMs still mix to form a new FCM causal knowledge graph. The mixing technique scales because it uses light computation with sparse causal chunk matrices. The mixing structure allows an operator-level type of Bayesian inference that produces "de-chunked" or posterior-like FCMs from the mixed FCM. These de-chunked FCMs are useful in their own right and allow further iterations of Bayesian updating. We demonstrate these mixing techniques on the essay text of Allison's "Thucydides Trap" model of conflict between a dominant power such as the United States and a rising power such as China. The FCM dynamical systems predict outcomes as they equilibrate to fixed-point or limit-cycle attractors. Seven out of 8 FCM knowledge graphs predicted a type of war when we stimulated them by turning on and keeping on the concept node that stands for the rising power's ambition and entitlement. Gemini 3.1 LLMs served as the chunking AI agents.
Read the full abstract

Computation and Language

Multi-agent AI systems outperform human teams in creativity

Tiancheng Hu, Yixuan Jiang, Haotian Li et al. (+5 more)

Although artificial intelligence (AI) now matches or exceeds human performance across numerous cognitive tasks, creativity remains a highly contested frontier. As AI systems based on large language models (LLMs) are increasingly adopted in research and innovation, it is essential to understand and augment their creativity. Here we demonstrate that multi-agent LLM teams not only surpass single agents, but also substantially outperform human teams in creativity (Cohen's d=1.50) across 4,541 multi-agent LLM ideas and 341 human-team ideas on six diverse problem-solving tasks. This advantage is driven by novelty while maintaining comparable usefulness. To investigate the generative processes in both groups, we represent conversations as paths through semantic space using neural language model representations. Both LLM and human teams produce more creative ideas when conversations range widely rather than staying centered on a single theme (low global coherence). However, the additional patterns that predict creativity differ: LLM teams benefit from efficient exploration (high semantic spread, shorter paths), while human teams benefit from maintaining smooth conversational flow (high local coherence, frequent pivots). Additionally, we identify model choice and discussion structure as orthogonal design levers that together explain 26.8% of variance in LLM conversational dynamics, paving the way for systematic approaches to developing multi-agent systems with augmented creative capabilities.
Read the full abstract

All authors Tiancheng Hu, Yixuan Jiang, Haotian Li, José Hernández-Orallo, Xing Xie, Nigel Collier, David Stillwell, Luning Sun

Computation and Language · Cross-listed from cs.LG

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents

Woongyeong Yeo, Yumin Choi, Taekyung Ki et al. (+1 more)

Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not which intermediate actions caused the outcome or how they should be corrected. Recent methods alleviate this issue by generating rewards or textual hints from turn-level action-output signals, or by using feedback-conditioned self-distillation. However, generating feedback at every turn is inefficient when many intermediate turns are already successful or neutral, and applying feedback at a fixed or misaligned turn often fails to supervise the actions that contributed to the failure. To bridge this gap, we propose HINT-SD, a targeted self-distillation framework that uses full-trajectory hindsight to select failure-relevant actions and applies feedback-conditioned distillation only to targeted action spans. Experiments on BFCL v3 and AppWorld show that our method outperforms the dense per-turn feedback baseline by up to 13.60 percentage points on average while achieving a 2.26$\times$ reduction in time per training step, suggesting that selecting where to distill is key to effective and efficient long-horizon agent training.
Read the full abstract

All authors Woongyeong Yeo, Yumin Choi, Taekyung Ki, Sung Ju Hwang

Computation and Language

PAREDA: A Multi-Accent Speech Dataset of Natural Language Processing Research Discussions

Sicheng Jin, Dipankar Srirag and Aditya Joshi

While modern Automatic Speech Recognition (ASR) systems achieve high accuracy on benchmark corpora, their performance often degrades when there is real-world variability. This work focuses on variability arising due to accented, spontaneous, and domain-specific speech. In particular, we introduce PAper REading DAtaset (PAREDA), a first-of-its-kind multi-accent speech dataset consisting of discussions on academic Natural Language Processing (NLP) papers between speakers with Australian, Indian-English, and Chinese English accents. Each session elicits a spontaneous monologue (a summary of a paper's abstract) and a non-monologue (a question-and-answer session between participants), resulting in a corpus rich with technical jargon and conversational phenomena. We evaluate the performance of SOTA ASR models on PAREDA, analysing the impact of accent mixing and increased speech rate. Our results show that, in the zero-shot setting, models perform worse, confirming the dataset's challenging nature. However, fine-tuning on PAREDA significantly reduces the Word Error Rate (WER), demonstrating that our dataset captures linguistic characteristics often missing from existing corpora. PAREDA serves as a valuable new resource for building and evaluating more robust and inclusive ASR systems for specialised, real-world applications.
Read the full abstract

Computation and Language

Generating Pretraining Tokens from Organic Data for Data-Bound Scaling

Zichun Yu and Chenyan Xiong

LLM pretraining is shifting from a compute-bound to a data-bound regime, where available human (organic) text falls far short of scaling demands. However, reaching the data-bound regime does not mean the model has fully utilized its organic corpus. In this paper, we introduce SynPro, a synthetic data generation framework that helps LLMs more thoroughly learn from limited organic data. SynPro applies two operations, rephrasing and reformatting, that present the same organic source in diverse forms to facilitate deeper learning without introducing external information. Both generators are optimized via reinforcement learning with quality, faithfulness, and data influence rewards, and are continuously updated as pretraining plateaus to target content the model has yet to absorb. We pretrain 400M, 1.1B, and 2B models with 10% of their Chinchilla-optimal tokens (0.8B, 2.2B, and 4B) from DCLM-Baseline, reflecting a realistic data-bound regime in frontier pretraining. Our results reveal that organic data is significantly underutilized by standard repetition: SynPro unlocks 3.4–5.2x the effective tokens of repetition, even surpassing the non-data-bound oracle that trains on equivalent unique data at the 1.1B and 2B scales. Analyses confirm that faithful, model-aware synthesis sustains data-bound scaling without causing distribution collapse. We open-source our code at https://github.com/cxcscmu/SynPro.
Read the full abstract

Computation and Language · Cross-listed from cs.AI

Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

Ahmad Al-Tawaha, Shangding Gu, Peizhi Niu et al. (+2 more)

Safety evaluations of memory-equipped LLM agents typically measure within-task safety: whether an agent completes a single scenario safely, often under adversarial conditions such as prompt injection or memory poisoning. In deployment, however, a single agent serves many independent tasks over a long horizon, and memory accumulated during earlier tasks can affect behavior on later, unrelated ones. Studying this regime requires evaluation along the temporal dimension across tasks: not whether an agent is safe at any single memory state, but how its safety profile changes as memory accumulates across many independent interactions. We call this failure mode temporal memory contamination. To isolate memory exposure from stream non-stationarity, we introduce a trigger-probe protocol that evaluates a fixed probe set against read-only memory snapshots at varying prefix lengths, together with a NullMemory counterfactual baseline for identifying memory-induced violations. We apply this protocol across three deployment scenarios spanning records, memos, forms, and email correspondence and eight memory architectures, and additionally on Claw-like AI agents, such as OpenClaw, using the platform's native memory mechanism. Memory-enabled agents consistently exceed the NullMemory baseline, and memory-induced violation rates show a robust upward trend with exposure length on both agent classes. Order-randomization experiments indicate that the effect is driven primarily by accumulated content rather than encounter order. Finally, a structural consequence of the event decomposition is that memory-induced risk is detectable from retrieval state before generation, which we confirm with a high-recall diagnostic monitor. Our results argue for treating memory safety as a longitudinal property that requires temporal evaluation, not a single-state property that can be captured by a snapshot.
Read the full abstract

All authors Ahmad Al-Tawaha, Shangding Gu, Peizhi Niu, Ruoxi Jia, Ming Jin

Computation and Language

SocialMemBench: Are AI Memory Systems Ready for Social Group Settings?

Olukunle Owolabi

Memory systems for AI assistants were built for single-user dialogue and fail characteristically when applied to multi-party social group settings. This gap matters for the social assistants being built today: group-acting agents embedded in chat platforms, and proactive personal-assistant agents whose holistic model of a user must include their social context. Existing memory benchmarks evaluate dyadic or workplace dialogue; none targets multi-party social groups, where memory must anchor facts in shared history rather than professional roles, separate group norms from individual exceptions, and correctly attribute even after member departure. We introduce SocialMemBench, a benchmark of human-verified synthetic social group networks across five archetypes (close friends, family, recreational, interest community, acquaintance network) and three group-size tiers (4-30 members), with 430 personas and 7,355 conversation turns, yielding 1,031 QA pairs across nine question categories. Each category isolates an architectural capability, and the five failure modes (single-stream conflation, temporal-state overwrite, entity merging at scale, missing cross-persona knowledge, norm-individual conflation) are testable hypotheses; our two research probes Subject-Mem and SMG provide evidence on two, three remain open. A full-context Gemini 2.5 Flash reference reaches only 0.721 against a blind-critic reasoning-model mean of 0.98 on small networks, indicating the benchmark is genuinely difficult even with complete access to the conversation. Across all 43 networks, the four open-source memory frameworks evaluated (Mem0, LangMem, Graphiti, Cognee) cluster in the 0.12-0.18 question-weighted range with overlapping 95% CIs, well below an uncompressed retrieval reference of 0.345 and a matched-answerer full-context reference of 0.369 (GPT-4o-mini). Current memory systems show a measurable gap.
Read the full abstract

Computation and Language

Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale

Jinghui Liu, Sarvesh Soni and Anthony Nguyen

Large language models (LLMs) can generate or synthesize clinical text for a wide range of applications, from improving clinical documentation to augmenting clinical text analytics. Yet evaluations typically focus on a narrow aspect – such as similarity or utility comparisons – even though these aspects are complementary and best viewed in parallel. In this study, we aim to conduct a systematic evaluation of LLM-generated clinical text, which includes intrinsic, extrinsic, and factuality evaluations of synthetic clinical notes rephrased from MIMIC databases at million-note scale. Our analysis demonstrates that synthetic notes preserve core clinical information and predictive utility for coarse-grained tasks despite substantial linguistic changes, but lose fine-grained details for task like ICD coding. We show this loss of detail can be substantially mitigated by rephrasing notes by chunks rather than by the whole note, but at the cost of reduced factual precision under incomplete context. Through fact-checking and error analysis, we further find that synthesis errors are dominated by misinterpretation of clinical context, alongside temporal confusion, measurement errors, and fabricated claims. Finally, we show that the synthetic notes – despite their task-agnostic nature – can effectively augment task-specific training for rare ICD codes.
Read the full abstract

Computation and Language

Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning

Yuval Shemla, Ayal Yakobe, Tanmay Agarwal et al. (+2 more)

Large language models are increasingly used as planning components in agentic systems, but current tool-use pipelines often require full tool schemas to be included in every prompt, creating substantial token overhead and limiting the practicality of smaller models. This paper investigates whether tool-use knowledge can be internalized into small language models through parameter-efficient fine-tuning, enabling structured planning without explicit tool descriptions at inference time. Using AssetOpsBench as the primary benchmark, we fine-tune Gemma 4 E4B and Qwen3-4B with 8-bit QLoRA on approximately 1,700 tool-use examples spanning tool knowledge, question-to-plan mappings, and execution-style traces. We evaluate the resulting models under description-free inference, where the prompt omits the tool catalog entirely. The fine-tuned models outperform an informed unfine-tuned baseline that receives full tool descriptions, reducing input length by 82.6% while improving structural and LLM-judge planning scores. In the best Gemma run, the model achieves an AT-F1 of 0.65 and an overall judge score of 3.88, compared with 0.47 and 2.88 for the informed baseline. Qwen3-4B achieves a strong overall judge score of 3.78 while using 62% less memory and running 2.5$\times$ faster than Gemma, though it also exhibits greater catastrophic forgetting on general multiple-choice benchmarks. Additional ablations show that LoRA rank controls a quality–retention trade-off, with $r=32$ maximizing planning quality and smaller ranks preserving more general knowledge. These results suggest that, for fixed tool catalogs, QLoRA fine-tuning can shift tool knowledge from prompt context into model weights, substantially reducing inference overhead while maintaining or improving tool-planning quality.
Read the full abstract

All authors Yuval Shemla, Ayal Yakobe, Tanmay Agarwal, Dhaval Patel, Kaoutar El Maghraoui