Peer Revenue Impact factor: volatile

Papers

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

Computer Science Computation and Language

cs.CL Watch Computation and Language

Monday 27 October

Computation and Language

MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs

Yucheng Ning, Xixun Lin, Fang Fang et al. (+1 more)

The widespread adoption of Large Language Models (LLMs) raises critical concerns about the factual accuracy of their outputs, especially in high-risk domains such as biomedicine, law, and education. Existing evaluation methods for short texts often fail on long-form content due to complex reasoning chains, intertwined perspectives, and cumulative information. To address this, we propose a systematic approach integrating large-scale long-form datasets, multi-agent verification mechanisms, and weighted evaluation metrics. We construct LongHalluQA, a Chinese long-form factuality dataset; and develop MAD-Fact, a debate-based multi-agent verification system. We introduce a fact importance hierarchy to capture the varying significance of claims in long-form texts. Experiments on two benchmarks show that larger LLMs generally maintain higher factual consistency, while domestic models excel on Chinese content. Our work provides a structured framework for evaluating and enhancing factual reliability in long-form LLM outputs, guiding their safe deployment in sensitive domains.
Read the full abstract

All authors Yucheng Ning, Xixun Lin, Fang Fang, Yanan Cao

Computation and Language

Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts

Anwesan Pal, Karen Hovsepian, Tinghao Guo et al. (+5 more)

Recent investigations into effective context lengths of modern flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and most impressive cadre of models. While approaches like retrieval-augmented generation (RAG) and chunk-based re-ranking attempt to mitigate this issue, they are sensitive to chunking, embedding and retrieval strategies and models, and furthermore, rely on extensive pre-processing, knowledge acquisition and indexing steps. In this paper, we propose Tagging-Augmented Generation (TAG), a lightweight data augmentation strategy that boosts LLM performance in long-context scenarios, without degrading and altering the integrity and composition of retrieved documents. We validate our hypothesis by augmenting two challenging and directly relevant question-answering benchmarks – NoLima and NovelQA – and show that tagging the context or even just adding tag definitions into QA prompts leads to consistent performance gains over the baseline – up to 17% for 32K token contexts, and 2.9% in complex reasoning question-answering for multi-hop queries requiring knowledge across a wide span of text. Additional details are available at https://sites.google.com/view/tag-emnlp.
Read the full abstract

All authors Anwesan Pal, Karen Hovsepian, Tinghao Guo, Mengnan Zhao, Somendra Tripathi, Nikos Kanakaris, George Mihaila, Sumit Nigam

Computation and Language

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

Liwei Jiang, Yuanjun Chai, Margaret Li et al. (+7 more)

Language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human thought through repeated exposure to similar outputs. Yet scalable methods for evaluating LM output diversity remain limited, especially beyond narrow tasks such as random number or name generation, or beyond repeated sampling from a single model. We introduce Infinity-Chat, a large-scale dataset of 26K diverse, real-world, open-ended user queries that admit a wide range of plausible answers with no single ground truth. We introduce the first comprehensive taxonomy for characterizing the full spectrum of open-ended prompts posed to LMs, comprising 6 top-level categories (e.g., brainstorm & ideation) that further breaks down to 17 subcategories. Using Infinity-Chat, we present a large-scale study of mode collapse in LMs, revealing a pronounced Artificial Hivemind effect in open-ended generation of LMs, characterized by (1) intra-model repetition, where a single model consistently generates similar responses, and more so (2) inter-model homogeneity, where different models produce strikingly similar outputs. Infinity-Chat also includes 31,250 human annotations, across absolute ratings and pairwise preferences, with 25 independent human annotations per example. This enables studying collective and individual-specific human preferences in response to open-ended queries. Our findings show that LMs, reward models, and LM judges are less well calibrated to human ratings on model generations that elicit differing idiosyncratic annotator preferences, despite maintaining comparable overall quality. Overall, INFINITY-CHAT presents the first large-scale resource for systematically studying real-world open-ended queries to LMs, revealing critical insights to guide future research for mitigating long-term AI safety risks posed by the Artificial Hivemind.
Read the full abstract

All authors Liwei Jiang, Yuanjun Chai, Margaret Li, Mickel Liu, Raymond Fok, Nouha Dziri, Yulia Tsvetkov, Maarten Sap, Alon Albalak, Yejin Choi

Computation and Language

Reinforcement Learning from Compiler and Language Server Feedback

Yifan Zhang and Lanser Contributors

Coding agents fail when text-level guesses outrun program facts: they hallucinate APIs, drift to the wrong symbol, and apply edits without evidence that the workspace remains valid. Compilers, type checkers, and language servers already compute the missing supervision signal, in the form of diagnostics, symbol resolution, type information, references, and refactoring preconditions, but expose it through interfaces designed for human-driven IDEs rather than learning loops. We introduce Reinforcement Learning from Compiler and Language Server Feedback (RLCSF) together with Lanser-CLI, a CLI-first orchestration layer that exposes this signal to agents and CI. RLCSF treats each tool interaction as a transition and computes a shaped process reward from deterministic changes in diagnostics, selector confidence, and edit safety. Lanser-CLI, in turn, converts ephemeral LSP sessions into replayable Analysis Bundles with pinned environment metadata and stable content hashes. Its core mechanisms are robust selectors that go beyond file:line:col, deterministic bundle normalization, preview-first guarded mutations, and a reward functional whose potential-based component is replayable under frozen snapshots. We formalize determinism for canonical bundles and prove that componentwise-improving transitions receive non-negative reward in the undiscounted setting. Together, these pieces yield a practical substrate for process supervision of coding agents.
Read the full abstract

Computation and Language · Cross-listed from cs.SI

Modeling Political Discourse with Sentence-BERT and BERTopic

Margarida Mendonca and Alvaro Figueira

Social media has reshaped political discourse, offering politicians a platform for direct engagement while reinforcing polarization and ideological divides. This study introduces a novel topic evolution framework that integrates BERTopic-based topic modeling with Moral Foundations Theory (MFT) to analyze the longevity and moral dimensions of political topics in Twitter activity during the 117th U.S. Congress. We propose a methodology for tracking dynamic topic shifts over time and measuring their association with moral values and quantifying topic persistence. Our findings reveal that while overarching themes remain stable, granular topics tend to dissolve rapidly, limiting their long-term influence. Moreover, moral foundations play a critical role in topic longevity, with Care and Loyalty dominating durable topics, while partisan differences manifest in distinct moral framing strategies. This work contributes to the field of social network analysis and computational political discourse by offering a scalable, interpretable approach to understanding moral-driven topic evolution on social media.
Read the full abstract

Computation and Language · Cross-listed from cs.LG

Offline Preference Optimization via Maximum Marginal Likelihood Estimation

Saeed Najafi and Alona Fyshe

Aligning Large Language Models (LLMs) with human preferences is crucial, but standard methods like Reinforcement Learning from Human Feedback (RLHF) are often complex and unstable. In this work, we propose a new, simpler approach that recasts alignment through the lens of Maximum Marginal Likelihood (MML) estimation. Our new MML based Preference Optimization (MMPO) maximizes the marginal log-likelihood of a preferred text output, using the preference pair as samples for approximation, and forgoes the need for both an explicit reward model and entropy maximization. We theoretically demonstrate that MMPO implicitly performs preference optimization, producing a weighted gradient that naturally up-weights chosen responses over rejected ones. Across models ranging from 135M to 8B parameters, we empirically show that MMPO: 1) is more stable with respect to the hyperparameter $\beta$ compared to alternative baselines, and 2) achieves competitive or superior preference alignment while better preserving the base model's general language capabilities. Through a series of ablation experiments, we show that this improved performance is indeed attributable to MMPO's implicit preference optimization within the gradient updates.
Read the full abstract

Sunday 26 October

Computation and Language · Cross-listed from q-bio.NC

Human-Centred Evaluation of Text-to-Image Generation Models for Self-expression of Mental Distress: A Dataset Based on GPT-4o

Sui He and Shenbin Qian

Effective communication is central to achieving positive healthcare outcomes in mental health contexts, yet international students often face linguistic and cultural barriers that hinder their communication of mental distress. In this study, we evaluate the effectiveness of AI-generated images in supporting self-expression of mental distress. To achieve this, twenty Chinese international students studying at UK universities were invited to describe their personal experiences of mental distress. These descriptions were elaborated using GPT-4o with four persona-based prompt templates rooted in contemporary counselling practice to generate corresponding images. Participants then evaluated the helpfulness of generated images in facilitating the expression of their feelings based on their original descriptions. The resulting dataset comprises 100 textual descriptions of mental distress, 400 generated images, and corresponding human evaluation scores. Findings indicate that prompt design substantially affects perceived helpfulness, with the illustrator persona achieving the highest ratings. This work introduces the first publicly available text-to-image evaluation dataset with human judgment scores in the mental health domain, offering valuable resources for image evaluation, reinforcement learning with human feedback, and multi-modal research on mental health communication.
Read the full abstract

Computation and Language

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

Canxiang Yan, Chunxiang Jin, Dawei Huang et al. (+22 more)

Existing speech models suffer from competing requirements on token representations by understanding and generation tasks. This discrepancy in representation prevents speech language models from performing instruction-based free-form editing. To solve this challenge, we introduce a novel framework that unifies speech understanding, generation, and editing. The core of our unified model is a unified continuous speech tokenizer MingTok-Audio, the first continuous tokenizer to effectively integrate semantic and acoustic features, which makes it suitable for both understanding and generation tasks. Based on this unified continuous audio tokenizer, we developed the speech language model Ming-UniAudio, which achieved a balance between generation and understanding capabilities. Ming-UniAudio sets new state-of-the-art (SOTA) records on 8 out of 12 metrics on the ContextASR benchmark. Notably, for Chinese voice cloning, it achieves a highly competitive Seed-TTS-WER of 0.95. Leveraging this foundational model, we further trained a dedicated speech editing model Ming-UniAudio-Edit, the first speech language model that enables universal, free-form speech editing guided solely by natural language instructions, handling both semantic and acoustic modifications without timestamp condition. To rigorously assess the editing capability and establish a foundation for future research, we introduce Ming-Freeform-Audio-Edit, the first comprehensive benchmark tailored for instruction-based free-form speech editing, featuring diverse scenarios and evaluation dimensions spanning semantic correctness, acoustic quality, and instruction alignment. We open-sourced the continuous audio tokenizer, the unified foundational model, and the free-form instruction-based editing model to facilitate the development of unified audio understanding, generation, and manipulation.
Read the full abstract

All authors Canxiang Yan, Chunxiang Jin, Dawei Huang, Haibing Yu, Han Peng, Hui Zhan, Jie Gao, Jing Peng, Jingdong Chen, Jun Zhou, Kaimeng Ren, Ming Yang, Mingxue Yang, Qiang Xu, Qin Zhao, Ruijie Xiong, Shaoxiong Lin, Xuezhi Wang, Yi Yuan, Yifei Wu, Yongjie Lyu, Zhengyu He, Zhihao Qiu, Zhiqiang Fang, Ziyuan Huang

Computation and Language

Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks

Peiyu Li, Xiuxiu Tang, Si Chen et al. (+4 more)

Evaluating large language models (LLMs) typically requires thousands of benchmark items, making the process expensive, slow, and increasingly impractical at scale. Existing evaluation protocols rely on average accuracy over fixed item sets, treating all items as equally informative despite substantial variation in difficulty and discrimination. We introduce ATLAS, an adaptive testing framework based on Item Response Theory (IRT) that estimates model ability using Fisher information-guided item selection. ATLAS reduces the number of required items by up to 90% while maintaining measurement precision. For instance, it matches whole-bank ability estimates using only 41 items (0.157 MAE) on HellaSwag (5,600 items). We further reconstruct accuracy from ATLAS's ability estimates and find that reconstructed accuracies closely match raw accuracies across all five benchmarks, indicating that ability ${\theta}$ preserves the global performance structure. At the same time, ${\theta}$ provides finer discrimination within accuracy-equivalent models: among more than 3,000 evaluated models, 23-31% shift by more than 10 rank positions, and models with identical accuracies receive meaningfully different ability estimates. Code and calibrated item banks are available at https://github.com/Peiyu-Georgia-Li/ATLAS.git.
Read the full abstract

All authors Peiyu Li, Xiuxiu Tang, Si Chen, Ying Cheng, Ronald Metoyer, Ting Hua, Nitesh V. Chawla

Computation and Language · Cross-listed from cs.CY

Chitchat with AI: Understand the supply chain carbon disclosure of companies worldwide through Large Language Model

Haotian Hang, Yueyang Shen, Vicky Zhu et al. (+2 more)

In the context of global sustainability mandates, corporate carbon disclosure has emerged as a critical mechanism for aligning business strategy with environmental responsibility. The Carbon Disclosure Project (CDP) hosts the world's largest longitudinal dataset of climate-related survey responses, combining structured indicators with open-ended narratives, but the heterogeneity and free-form nature of these disclosures present significant analytical challenges for benchmarking, compliance monitoring, and investment screening. This paper proposes a novel decision-support framework that leverages large language models (LLMs) to assess corporate climate disclosure quality at scale. It develops a master rubric that harmonizes narrative scoring across 11 years of CDP data (2010-2020), enabling cross-sector and cross-country benchmarking. By integrating rubric-guided scoring with percentile-based normalization, our method identifies temporal trends, strategic alignment patterns, and inconsistencies in disclosure across industries and regions. Results reveal that sectors such as technology and countries like Germany consistently demonstrate higher rubric alignment, while others exhibit volatility or superficial engagement, offering insights that inform key decision-making processes for investors, regulators, and corporate environmental, social, and governance (ESG) strategists. The proposed LLM-based approach transforms unstructured disclosures into quantifiable, interpretable, comparable, and actionable intelligence, advancing the capabilities of AI-enabled decision support systems (DSSs) in the domain of climate governance.
Read the full abstract

All authors Haotian Hang, Yueyang Shen, Vicky Zhu, Jose Cruz, Michelle Li

Computation and Language

Correctness Forensics for Batch Speculative Decoding: Diagnosing the Ragged Tensor Problem

Ranran Haoran Zhang, Soumik Dey, Ashirbad Mishra et al. (+3 more)

Inference optimizations are routinely evaluated by throughput alone, without verifying output correctness. We conduct a forensic analysis of batch speculative decoding and find that several widely-used implementations silently produce corrupted outputs (repetitive tokens, <unk> symbols) while reporting competitive speed; failures invisible to metrics like ROUGE. We trace the root cause to the ragged tensor problem: variable token acceptance desynchronizes position IDs, attention masks, and KV-cache across a batch. We formalize the synchronization invariants (rectangular alignment and position-ID contiguity) that valid batched inference must preserve and show that maintaining them incurs superlinear alignment overhead under contiguous layouts. EQSPEC enforces the invariants without custom kernels; EXSPEC schedules same-length sequences to bypass realignment. On SpecBench across three model families, EXSPEC reaches 3 x throughput at batch size 8 with 95% exact match to standard decoding; residual divergence traces to floating-point non-determinism, not synchronization error. Code:https://github.com/eBay/spec_dec
Read the full abstract

All authors Ranran Haoran Zhang, Soumik Dey, Ashirbad Mishra, Hansi Wu, Binbin Li, Rui Zhang

Computation and Language

A Comprehensive Dataset for Human vs. AI Generated Text Detection

Rajarshi Roy, Gurpreet Singh, Ashhar Aziz et al. (+17 more)

The rapid advancement of large language models (LLMs) has led to increasingly human-like AI-generated text, raising concerns about content authenticity, misinformation, and trustworthiness. Addressing the challenge of reliably detecting AI-generated text and attributing it to specific models requires large-scale, diverse, and well-annotated datasets. In this work, we present a comprehensive dataset comprising over 73,193 text samples that combine authentic New York Times articles with synthetic versions generated by multiple state-of-the-art LLMs including Gemma-2-9b, Mistral-7B, Qwen-2-72B, LLaMA-8B, Yi-Large, and GPT-4-o. The dataset provides original article abstracts as prompts, full human-authored narratives. We establish baseline results for two key tasks: distinguishing human-written from AI-generated text, achieving an accuracy of 58.35%, and attributing AI texts to their generating models with an accuracy of 8.92%. By bridging real-world journalistic content with modern generative models, the dataset aims to catalyze the development of robust detection and attribution methods, fostering trust and transparency in the era of generative AI. Our dataset is available at: https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Text_Dataset
Read the full abstract

All authors Rajarshi Roy, Gurpreet Singh, Ashhar Aziz, Shashwat Bajpai, Nasrin Imanpour, Shwetangshu Biswas, Kapil Wanaskar, Parth Patwa, Subhankar Ghosh, Shreyas Dixit, Nilesh Ranjan Pal, Vipula Rawte, Ritvik Garimella, Gaytri Jena, Amitava Das, Amit Sheth, Vasu Sharma, Aishwarya Naresh Reganti, Vinija Jain, Aman Chadha

Computation and Language

Interpreting and Mitigating Unwanted Uncertainty in LLMs

Tiasa Singha Roy, Ayush Rajesh Jhaveri and Ilias Triantafyllopoulos

Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect one when re-prompted. This behavior undermines trust and poses serious risks in high-stakes domains. In this work, we investigate the mechanisms that drive this phenomenon. We adapt the Needle-in-a-Haystack retrieval framework and integrate a Flip-style re-evaluation prompt to simulate realistic answer-flipping scenarios. We find that retrieval heads are not primarily responsible for avoiding uncertainty. Instead, we identify a small set of non-retrieval attention heads that disproportionately attend to misleading tokens in uncertain contexts. Masking these heads yields significant improvements, reducing flip behavior by up to 15% without introducing incoherence or overcorrection. However, when tested for downstream tasks, we observe trade-offs with flip behavior. Our findings contribute to the growing field of mechanistic interpretability and present a simple yet effective technique for mitigating uncertainty-driven failure modes in LLMs.
Read the full abstract

Computation and Language

Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement

Linyang He, Tianjun Zhong, Richard Antonello et al. (+3 more)

Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model neural responses to language, their internal representations are highly "entangled," mixing information about lexicon, syntax, meaning, and reasoning. This entanglement biases conventional brain encoding analyses toward linguistically shallow features (e.g., lexicon and syntax), making it difficult to isolate the neural substrates of cognitively deeper processes. Here, we introduce a residual disentanglement method that computationally isolates these components. By first probing an LM to identify feature-specific layers, our method iteratively regresses out lower-level representations to produce four nearly orthogonal embeddings for lexicon, syntax, meaning, and, critically, reasoning. We used these disentangled embeddings to model intracranial (ECoG) brain recordings from neurosurgical patients listening to natural speech. We show that: 1) This isolated reasoning embedding exhibits unique predictive power, accounting for variance in neural activity not explained by other linguistic features and even extending to the recruitment of visual regions beyond classical language areas. 2) The neural signature for reasoning is temporally distinct, peaking later (~350-400ms) than signals related to lexicon, syntax, and meaning, consistent with its position atop a processing hierarchy. 3) Standard, non-disentangled LLM embeddings can be misleading, as their predictive success is primarily attributable to linguistically shallow features, masking the more subtle contributions of deeper cognitive processing.
Read the full abstract

All authors Linyang He, Tianjun Zhong, Richard Antonello, Gavin Mischler, Micah Goldblum, Nima Mesgarani

Computation and Language

Once Upon an Input: Reasoning via Per-Instance Program Synthesis

Adam Stein, Neelay Velingker, Mayur Naik et al. (+1 more)

Large language models (LLMs) excel at zero-shot inference but continue to struggle with complex, multi-step reasoning. Recent methods that augment LLMs with intermediate reasoning steps such as Chain of Thought (CoT) and Program of Thought (PoT) improve performance but often produce undesirable solutions, especially in algorithmic domains. We introduce Per-Instance Program Synthesis (PIPS), a method that generates and refines programs at the instance-level using structural feedback without relying on task-specific guidance or explicit test cases. To further improve performance, PIPS incorporates a confidence metric that dynamically chooses between direct inference and program synthesis on a per-instance basis. Experiments across three frontier LLMs and 30 benchmarks including all tasks of Big Bench Extra Hard (BBEH), visual question answering tasks, relational reasoning tasks, and mathematical reasoning tasks show that PIPS improves the absolute harmonic mean accuracy by up to 8.6% and 9.4% compared to PoT and CoT respectively, and reduces undesirable program generations by 65.1% on the algorithmic tasks compared to PoT with Gemini-2.0-Flash.
Read the full abstract

All authors Adam Stein, Neelay Velingker, Mayur Naik, Eric Wong

Computation and Language

Leveraging Large Language Models to Identify Conversation Threads in Collaborative Learning

Prerna Ravi, Dong Won Lee, Beatriz Flamia et al. (+5 more)

Understanding how ideas develop and flow in small-group conversations is critical for analyzing collaborative learning. A key structural feature of these interactions is threading, the way discourse talk naturally organizes into interwoven topical strands that evolve over time. While threading has been widely studied in asynchronous text settings, detecting threads in synchronous spoken dialogue remains challenging due to overlapping turns and implicit cues. At the same time, large language models (LLMs) show promise for automating discourse analysis but often struggle with long-context tasks that depend on tracing these conversational links. In this paper, we investigate whether explicit thread linkages can improve LLM-based coding of relational moves in group talk. We contribute a systematic guidebook for identifying threads in synchronous multi-party transcripts and benchmark different LLM prompting strategies for automated threading. We then test how threading influences performance on downstream coding of conversational analysis frameworks, that capture core collaborative actions such as agreeing, building, and eliciting. Our results show that providing clear conversational thread information improves LLM coding performance and underscores the heavy reliance of downstream analysis on well-structured dialogue. We also discuss practical trade-offs in time and cost, emphasizing where human-AI hybrid approaches can yield the best value. Together, this work advances methods for combining LLMs and robust conversational thread structures to make sense of complex, real-time group interactions.
Read the full abstract

All authors Prerna Ravi, Dong Won Lee, Beatriz Flamia, Jasmine David, Brandon Hanks, Cynthia Breazeal, Emma Anderson, Grace Lin

Computation and Language

Exploration of Summarization by Generative Language Models for Automated Scoring of Long Essays

Haowei Hua, Hong Jiao and Xinyi Wang

BERT and its variants are extensively explored for automated scoring. However, a limit of 512 tokens for these encoder-based models showed the deficiency in automated scoring of long essays. Thus, this research explores generative language models for automated scoring of long essays via summarization and prompting. The results revealed great improvement of scoring accuracy with QWK increased from 0.822 to 0.8878 for the Learning Agency Lab Automated Essay Scoring 2.0 dataset.
Read the full abstract

Computation and Language

Cross-Lingual Stability and Bias in Instruction-Tuned Language Models for Humanitarian NLP

Poli Nemkova, Amrit Adhikari, Matthew Pearson et al. (+2 more)

Humanitarian organizations face a critical choice: invest in costly commercial APIs or rely on free open-weight models for multilingual human rights monitoring. While commercial systems offer reliability, open-weight alternatives lack empirical validation – especially for low-resource languages common in conflict zones. This paper presents the first systematic comparison of commercial and open-weight large language models (LLMs) for human-rights-violation detection across seven languages, quantifying the cost-reliability trade-off facing resource-constrained organizations. Across 78,000 multilingual inferences, we evaluate six models – four instruction-aligned (Claude-Sonnet-4, DeepSeek-V3, Gemini-Flash-2.0, GPT-4.1-mini) and two open-weight (LLaMA-3-8B, Mistral-7B) – using both standard classification metrics and new measures of cross-lingual reliability: Calibration Deviation (CD), Decision Bias (B), Language Robustness Score (LRS), and Language Stability Score (LSS). Results show that alignment, not scale, determines stability: aligned models maintain near-invariant accuracy and balanced calibration across typologically distant and low-resource languages (e.g., Lingala, Burmese), while open-weight models exhibit significant prompt-language sensitivity and calibration drift. These findings demonstrate that multilingual alignment enables language-agnostic reasoning and provide practical guidance for humanitarian organizations balancing budget constraints with reliability in multilingual deployment.
Read the full abstract

All authors Poli Nemkova, Amrit Adhikari, Matthew Pearson, Vamsi Krishna Sadu, Mark V. Albert

Computation and Language

VEHME: A Vision-Language Model For Evaluating Handwritten Mathematics Expressions

Thu Phuong Nguyen, Duc M. Nguyen, Hyotaek Jeon et al. (+4 more)

Automatically assessing handwritten mathematical solutions is an important problem in educational technology with practical applications, but it remains a significant challenge due to the diverse formats, unstructured layouts, and symbolic complexity of student work. To address this challenge, we introduce VEHME-a Vision-Language Model for Evaluating Handwritten Mathematics Expressions-designed to assess open-form handwritten math responses with high accuracy and interpretable reasoning traces. VEHME integrates a two-phase training pipeline: (i) supervised fine-tuning using structured reasoning data, and (ii) reinforcement learning that aligns model outputs with multi-dimensional grading objectives, including correctness, reasoning depth, and error localization. To enhance spatial understanding, we propose an Expression-Aware Visual Prompting Module, trained on our synthesized multi-line math expressions dataset to robustly guide attention in visually heterogeneous inputs. Evaluated on AIHub and FERMAT datasets, VEHME achieves state-of-the-art performance among open-source models and approaches the accuracy of proprietary systems, demonstrating its potential as a scalable and accessible tool for automated math assessment. Our training and experiment code is publicly available at our GitHub repository.
Read the full abstract

All authors Thu Phuong Nguyen, Duc M. Nguyen, Hyotaek Jeon, Hyunwook Lee, Hyunmin Song, Sungahn Ko, Taehwan Kim

Computation and Language · Cross-listed from cs.AI

How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations

Zora Zhiruo Wang, Yijia Shao, Omar Shaikh et al. (+3 more)

AI agents are continually optimized for tasks related to human work, such as software engineering and professional writing, signaling a pressing trend with significant impacts on the human workforce. However, these agent developments have often not been grounded in a clear understanding of how humans execute work, to reveal what expertise agents possess and the roles they can play in diverse workflows. In this work, we study how agents do human work by presenting the first direct comparison of human and agent workers across multiple essential work-related skills: data analysis, engineering, computation, writing, and design. To better understand and compare heterogeneous computer-use activities of workers, we introduce a scalable toolkit to induce interpretable, structured workflows from either human or agent computer-use activities. Using such induced workflows, we compare how humans and agents perform the same tasks and find that: (1) While agents exhibit promise in their alignment to human workflows, they take an overwhelmingly programmatic approach across all work domains, even for open-ended, visually dependent tasks like design, creating a contrast with the UI-centric methods typically used by humans. (2) Agents produce work of inferior quality, yet often mask their deficiencies via data fabrication and misuse of advanced tools. (3) Nonetheless, agents deliver results 88.3% faster and cost 90.4-96.2% less than humans, highlighting the potential for enabling efficient collaboration by delegating easily programmable tasks to agents.
Read the full abstract

All authors Zora Zhiruo Wang, Yijia Shao, Omar Shaikh, Daniel Fried, Graham Neubig, Diyi Yang

Computation and Language

Scalable Supervision for Software Agents via Patch Reasoning

Junjielong Xu, Boyin Tan, Xiaoyuan Liu et al. (+3 more)

While language model agents have advanced software engineering, existing test-based supervision is limiting its scalability on real-world issues. The reason is twofold: (1) high-coverage tests are naturally rare in the wild, and (2) building and running test sandbox is heavy and fragile. To unlock supervision scaling, we propose R4P, a reasoning-based method that provides scaffold-agnostic rewards. R4P uses a group-wise training objective, enabling it to verify multiple patches against each other's modification and gain a dense reward for supervising agents without executing tests or relying on specific agent trajectories. R4P achieves 72.2% Acc. for verifying patches from SWE-bench, competitive with proprietary models. To show the downstream practical utility of R4P, we design and train an execution-free scaffold, Mini-SE, with pure RL via R4P. Mini-SE achieves 26.2% Pass@1, showing a 10.0% improvement over the original Qwen3-32B, and can be further improved to 32.8% with R4P for test-time scaling on patch selection. The stable scaling curves illustrate that though imperfect, R4P can still reliably support downstream tasks at scale.
Read the full abstract

All authors Junjielong Xu, Boyin Tan, Xiaoyuan Liu, Chao Peng, Pengfei Gao, Pinjia He

Computation and Language

Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion

Haoyi Qiu, Yilun Zhou, Pranav Narayanan Venkit et al. (+4 more)

As autonomous agents increasingly interact, they inevitably attempt to influence one another. While prior work in text-only settings has explored the dynamics of Agent-to-Agent (A2A) persuasion, the rise of Vision-Language Models (VLMs) introduces a more complex challenge: multimodal content conveys richer information while integrating subtle, hard-to-detect persuasive cues. To study this vulnerability, we present MMPersuade, a unified framework and dataset for A2A multimodal persuasion. We model interactions between a persuader agent, which leverages images and psychological strategies, and a persuadee VLM. Our benchmark spans commercial, subjective and behavioral, and adversarial contexts, and evaluates persuasion via function-calling that capture behavioral shifts beyond verbal responses. Experiments on six VLMs reveal three findings: (1) multimodal inputs consistently outperform text-only persuasion, with raw visual signals uniquely increasing susceptibility in adversarial settings by bypassing text-activated safety defenses; (2) persuadee vulnerability is highly domain- and format-dependent, with realistic and community-style formats driving susceptibility in commercial settings while different formats dominate in adversarial ones; and (3) psychological strategy efficacy varies with context and model architecture, as more capable models resist benign persuasion yet become more susceptible under adversarial multimodal inputs. Our framework provides a foundation for building more robust and aligned VLMs in multi-agent environments.
Read the full abstract

All authors Haoyi Qiu, Yilun Zhou, Pranav Narayanan Venkit, Kung-Hsiang Huang, Jiaxin Zhang, Nanyun Peng, Chien-Sheng Wu

Computation and Language · Cross-listed from cs.LG

TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination

Omar Naim, Krish Sharma, Niyar R Barman et al. (+1 more)

Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (Task-Aware Layer Elimination), an inference-time method that improves task performance by selectively removing layers that are irrelevant or detrimental for a given task. TALE optimizes task-specific performance, yielding a task-optimized architecture without retraining. Across 9 tasks and 5 model families, under both zero-shot and few-shot settings, TALE consistently matches or surpasses baseline performance while simultaneously reducing computational costs. TALE also synergizes with fine-tuning, leading to further performance improvements. Computing TALE for a new task requires modest resources, making it a practical and deployable solution for task-specialized LLM inference.
Read the full abstract

All authors Omar Naim, Krish Sharma, Niyar R Barman, Nicholas Asher

Computation and Language

Iterative Layer Pruning for Efficient Translation Inference

Yasmin Moslem, Muhammad Hazim Al Farouq and John D. Kelleher

Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requirements. In this paper, we address this challenge and present our submissions to the Model Compression track at the Conference on Machine Translation (WMT 2025). In our experiments, we investigate iterative layer pruning guided by layer importance analysis. We evaluate this method using the Aya-Expanse-8B model for translation from Czech to German, and from English to Egyptian Arabic. Our approach achieves substantial reductions in model size and inference time, while maintaining the translation quality of the baseline models.
Read the full abstract

Computation and Language

EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models

Li Zhou, Lutong Yu, You Lyu et al. (+6 more)

Speech Language Models (SLMs) have made significant progress in spoken language understanding. Yet it remains unclear whether they can fully perceive non lexical vocal cues alongside spoken words, and respond with empathy that aligns with both emotional and contextual factors. Existing benchmarks typically evaluate linguistic, acoustic, reasoning, or dialogue abilities in isolation, overlooking the integration of these skills that is crucial for human-like, emotionally intelligent conversation. We present EchoMind, the first interrelated, multi-level benchmark that simulates the cognitive process of empathetic dialogue through sequential, context-linked tasks: spoken-content understanding, vocal-cue perception, integrated reasoning, and response generation. All tasks share identical and semantically neutral scripts that are free of explicit emotional or contextual cues, and controlled variations in vocal style are used to test the effect of delivery independent of the transcript. EchoMind is grounded in an empathy-oriented framework spanning 3 coarse and 12 fine-grained dimensions, encompassing 39 vocal attributes, and evaluated using both objective and subjective metrics. Testing 12 advanced SLMs reveals that even state-of-the-art models struggle with high-expressive vocal cues, limiting empathetic response quality. Analyses of prompt strength, speech source, and ideal vocal cue recognition reveal persistent weaknesses in instruction-following, resilience to natural speech variability, and effective use of vocal cues for empathy. These results underscore the need for SLMs that integrate linguistic content with diverse vocal cues to achieve truly empathetic conversational ability.
Read the full abstract

All authors Li Zhou, Lutong Yu, You Lyu, Yihang Lin, Zefeng Zhao, Junyi Ao, Yuhao Zhang, Benyou Wang, Haizhou Li

Computation and Language

Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models

Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini et al. (+2 more)

In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic memory, where the retrieval of specific events is enabled by separating events that happened at different times, this work probes the ability of various pretrained LLMs, including transformer and state-space models, to differentiate and retrieve temporally separated events. Specifically, we prompted models with sequences containing multiple presentations of the same token, which reappears at the sequence end. By fixing the positions of these repeated tokens and permuting all others, we removed semantic confounds and isolated temporal effects on next-token prediction. Across diverse sequences, models consistently placed the highest probabilities on tokens following a repeated token, but with a notable bias for those nearest the beginning or end of the input. An ablation experiment linked this phenomenon in transformers to induction heads. Extending the analysis to unique semantic contexts with partial overlap further demonstrated that memories embedded in the middle of a prompt are retrieved less reliably. Despite architectural differences, state-space and transformer models showed comparable temporal biases. Our findings deepen the understanding of temporal biases in in-context learning and offer an illustration of how these biases can enable temporal separation and episodic retrieval.
Read the full abstract

All authors Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini, Yash Aggarwal, Zoran Tiganj

Computation and Language · Cross-listed from cs.AI

Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models

Piyushkumar Patel

While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major barrier to deploying these models in real-world applications where accuracy matters. We developed a fact verification framework that catches and corrects these errors in real-time by cross checking LLM outputs against multiple knowledge sources. Our system combines structured databases, live web searches, and academic literature to verify factual claims as they're generated. When we detect inconsistencies, we automatically correct them while preserving the natural flow of the response. Testing across various domains showed we could reduce hallucinations by 67% without sacrificing response quality. Domain experts in healthcare, finance, and scientific research rated our corrected outputs 89% satisfactory a significant improvement over unverified LLM responses. This work offers a practical solution for making LLMs more trustworthy in applications where getting facts wrong isn't an option.
Read the full abstract

Computation and Language

Low-Resource Dialect Adaptation of Large Language Models: A French Dialect Case-Study

Eeham Khan, Firas Saidani, Owen Van Esbroeck et al. (+2 more)

Despite the widespread adoption of Large Language Models (LLMs), their strongest capabilities remain largely confined to a small number of high-resource languages for which there is abundant training data. Recently, continual pre-training (CPT) has emerged as a means to fine-tune these models to low-resource regional dialects. In this paper, we study the use of CPT for dialect learning under tight data and compute budgets. Using low-rank adaptation (LoRA) and compute-efficient continual pre-training, we adapt three LLMs to the Québec French dialect using a very small dataset and benchmark them on the COLE suite. Our experiments demonstrate an improvement on the minority dialect benchmarks with minimal regression on the prestige language benchmarks with around 1% of model parameters updated. Analysis of the results demonstrate that gains are highly contingent on corpus composition. These findings indicate that CPT with parameter-efficient fine-tuning (PEFT) can narrow the dialect gap by providing cost-effective and sustainable language resource creation, expanding high-quality LLM access to minority linguistic communities. To support reproducibility and broaden access, we release the first Québec French LLMs on Hugging Face.
Read the full abstract

All authors Eeham Khan, Firas Saidani, Owen Van Esbroeck, Richard Khoury, Leila Kosseim

Computation and Language · Cross-listed from cs.IR

REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization

Yiwen Tang, Qiuyu Zhao, Zenghui Sun et al. (+3 more)

In Taobao e-commerce visual search, user behavior analysis reveals a large proportion of no-click requests, suggesting diverse and implicit user intents. These intents are expressed in various forms and are difficult to mine and discover, thereby leading to the limited adaptability and lag in platform strategies. This greatly restricts users' ability to express diverse intents and hinders the scalability of the visual search system. This mismatch between user implicit intent expression and system response defines the User-SearchSys Intent Discrepancy. To alleviate the issue, we propose a novel framework REVISION. This framework integrates offline reasoning mining with online decision-making and execution, enabling adaptive strategies to solve implicit user demands. In the offline stage, we construct a periodic pipeline to mine discrepancies from historical no-click requests. Leveraging large models, we analyze implicit intent factors and infer optimal suggestions by jointly reasoning over query and product metadata. These inferred suggestions serve as actionable insights for refining platform strategies. In the online stage, REVISION-R1-3B, trained on the curated offline data, performs holistic analysis over query images and associated historical products to generate optimization plans and adaptively schedule strategies across the search pipeline. Our framework offers a streamlined paradigm for integrating large models with traditional search systems, enabling end-to-end intelligent optimization across information aggregation and user interaction. Experimental results demonstrate that our approach improves the efficiency of implicit intent mining from large-scale search logs and significantly reduces the no-click rate.
Read the full abstract

All authors Yiwen Tang, Qiuyu Zhao, Zenghui Sun, Jinsong Lan, Xiaoyong Zhu, Bo Zheng

Computation and Language

E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search

Qi Liu, Yanzhao Zhang, Mingxin Li et al. (+3 more)

Text embedding models deliver competitive retrieval performance with high efficiency, but their ranking fidelity remains limited compared to LLM-based listwise rerankers, which capture fine-grained query-document and document-document interactions at high computational cost. We propose E2Rank (Efficient Embedding-based Ranking), a unified framework that extends a single text embedding model to perform both retrieval and listwise reranking via continued training under a listwise ranking objective. The key insight is to treat the listwise prompt—constructed from the query and its top-K candidates—as a pseudo-relevance feedback (PRF) query, enabling reranking via cosine similarity against precomputed document embeddings without autoregressive decoding. Empirically, E2Rank achieves state-of-the-art results on BEIR, competitive performance on the reasoning-intensive BRIGHT benchmark, significantly lower latency than existing LLM-based rerankers, and improved embedding performance on MTEB—all within a single model.
Read the full abstract

All authors Qi Liu, Yanzhao Zhang, Mingxin Li, Dingkun Long, Pengjun Xie, Jiaxin Mao