cs.CL · 2026-08-25 · No. 95

Computation and Language, 2026-08-25.

25 new papers in cs.CL. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

25 entries
  1. 01

    SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?

    Deyao Hong, Yizhe Chi, Wenyi Li, Xiaoqiu Wang, Mingju Gao, Kaisen Yang, Bingxiang He, Youjie Zheng, Calvin Xiao, Qinhuai Na

    cs.CL · cs.AI · cs.SE

    Modern software systems accumulate technical debt over decades of development, which makes migration expensive and largely manual. As coding agents become increasingly capable at bug fixing, can they autonomously perform such migrations? Existing benchmarks cannot answer this question because they evaluate only behavioural correctness, not whether the migration actually occurred. This leads an easy hack: agents copy the original...

    arxiv.org/abs/2608.23564 · PDF

  2. 02

    ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings

    Na Li, Yuchen Jiao, Changxiao Cai, Gen Li

    cs.CL · cs.AI · cs.LG · stat.ML

    Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existing continuous frameworks still rely on decoders supervised with cross entropy (CE) because the flow trajectories are not guaranteed to terminate at valid token embeddings. Motivated by this limitation, we introduce \textbf{ConvergeFlow}, an embedding-space flow-based LM, which constrains the data...

    arxiv.org/abs/2608.23551 · PDF

  3. 03

    When Names Cross Scripts: A Source-Grounded Benchmark for Historical Entity Reconciliation in the Mongol World

    Xiang Chen, Zeyu Zhang

    cs.CL · cs.AI

    Historical people may appear under different languages, scripts, and transcription traditions, while distinct individuals may share highly similar or even identical names. This makes historical identity reconciliation more than a problem of string matching or transliteration. We introduce MHER, a provenance-controlled benchmark for pairwise reconciliation of person-name attestations from the Mongol world. MHER contains a balanced 396-pair...

    arxiv.org/abs/2608.23507 · PDF

  4. 04

    What's the Catch? Evaluating Temporal Consistency in Vision-Language Models

    Marek Hradil, Danae Sánchez Villegas

    cs.CL · cs.AI · cs.CV

    Vision-language models (VLMs) achieve strong performance on video and image-sequence benchmarks, yet it remains unclear whether they capture temporal structure. To study this question, we formulate temporal grounding as an anomaly detection problem, providing a simple and controlled evaluation that directly tests sensitivity to temporal consistency. We introduce TimeCatch, where temporal anomalies are created by swapping consecutive frames...

    arxiv.org/abs/2608.23474 · PDF

  5. 05

    Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data

    Yifei Song, Kun Efimov-Zhang, Claire Gardent

    cs.CL · cs.AI

    Structured data exists in many forms (tables, knowledge graphs, charts, and time series), and converting it into text may involve different generation tasks. However, most prior work on data-to-text (D2T) generation has focused on specific tasks and datasets, relying either on task-specific training data or on the zero-shot capabilities of large language models. We study cross-domain D2T generation in a setting where neither in-domain...

    arxiv.org/abs/2608.23391 · PDF

  6. 06

    Cross-lingual Biography Enrichment via Claim Extraction and Alignment

    Yifei Song, Ziyang Chen, Emil Sayilov, Claire Gardent

    cs.CL · cs.AI

    English Wikipedia is often treated as the default encyclopedic source, yet non-English Wikipedia editions can contain richer locally grounded information for long-tail figures. We study cross-lingual biography enrichment: enriching an existing English biography with facts supported by a non-English biography about the same person. Focusing on women from non-English-speaking contexts, we introduce \textsc{CLAW-4L}, a benchmark consisting of...

    arxiv.org/abs/2608.23390 · PDF

  7. 07

    The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning

    Matthew Perlman, Atharva Nijasure, James Allan

    cs.CL · cs.AI · cs.IR

    LoRA fine-tuning is standard for adapting LLMs to reranking, but it remains unclear where in the network task-specific relevance behavior is learned and what attention-level changes accompany that learning. Through ablation and attention experiments, we identify where LoRA attention updates to RankLLaMA improve performance and whether those gains coincide with interpretable relevance-oriented attention patterns such as lexical matching,...

    arxiv.org/abs/2608.23338 · PDF

  8. 08

    Future Querying: Can LLMs Serve as Implicit Medical World Models?

    Siri Willems, James Butterworth, Lore Goetschalckx, Peter Vrancx, Philippe Modard, Elke Giets, Ludovic Denoyer

    cs.CL · cs.AI

    Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured text. To address this, we introduce future querying, a paradigm that probes whether large language models (LLMs) can function as implicit medical world models by evaluating their ability to answer time-indexed clinical queries about a patient's future. Our framework operates on unstructured...

    arxiv.org/abs/2608.23248 · PDF

  9. 09

    Credal Large Language Models for Semantic Commitment under Uncertainty

    Shireen Kudukkil Manchingal, Sofiia Nikolenko, Fabio Cuzzolin

    cs.CL · cs.AI · cs.LG · stat.ML

    Large language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence. A central limitation is that standard LLMs represent uncertainty through a single predictive distribution, conflating epistemic ignorance with genuine ambiguity. We introduce Credal Large Language Models (CLLMs): an ensemble of LoRA adapters induces a credal set whose lower and upper probabilities expose the spread of plausible predictive...

    arxiv.org/abs/2608.23244 · PDF

  10. 10

    Language Chain in Alignment: Cross-Lingual Ranking Preference Optimization

    Seungyoon Lee, Minhyuk Kim, Jungseob Lee, Heuiseok Lim

    cs.CL · cs.AI

    The alignment of Large Language Models heavily relies on English-centric high-quality preference data, which often leads to suboptimal performance in other languages. In this paper, we propose Cross-Lingual Ranking Preference Optimization (CRPO), a novel framework that leverages robust preference knowledge from English to facilitate preference alignment in the target language. We design a hierarchical structure within parallel preference...

    arxiv.org/abs/2608.23149 · PDF

  11. 11

    LITERARYBIGFIVE: Author-Personalized Text Generation in a Unified Interpretable Space

    Jinghui Zhang, Lang Gao, Ao Li, Mingzhe Li, Ruihong Zeng, Zirui Song, Kentaro Inui, Xiuying Chen

    cs.CL · cs.AI

    Personalized text generation for authors and literary writing is essential for applications such as adaptive writing assistants, creative support tools, and computational literary analysis. However, existing approaches to author modeling and personalization often represent writing behavior as independent labels, requiring large-scale corpus collection or fine-tuning for each author or stylistic category. Such formulations are costly,...

    arxiv.org/abs/2608.23124 · PDF

  12. 12

    Statistical Machine Translation Systems of English-Pnar Language Pair : Some Insights of the Emperical Study

    Edawanbiang Dhar Surmila Thokchom, Thoudam Doren Singh

    cs.CL · cs.AI

    Pnar, an Austroasiatic language spoken by approximately 0.4 million people in the Jaintia Hills of Meghalaya, lacks the digital corpora and natural language processing (NLP) resources. This paper presents the first machine translation study for the English and Pnar language pair. Using articles collected from the Wyrta newspaper, we built a parallel corpus comprising of 10,234 sentences and trained phrase-based statistical machine translation...

    arxiv.org/abs/2608.23120 · PDF

  13. 13

    Molecular LLM Agents: From Architectural Design to Scientific Autonomy

    Jiatong Li, Wengyu Zhang, Weida Wang, Yuxuan Ren, Wei Liu, Chenyang Mao, Yuqiang Li, Yatao Bian, Changmeng Zheng,...

    cs.CL · cs.AI

    Molecular science represents an important frontier for LLM-based agents. Unlike general agents that mainly operate over natural language, code, or web environments, molecular LLM agents must perceive, reason about, and act upon chemical objects across symbolic strings, molecular graphs, 3D conformations, spectra, simulations, and wet-lab measurements. Their capabilities depend on chemically faithful molecular perception, an LLM-centered agent...

    arxiv.org/abs/2608.23104 · PDF

  14. 14

    Beyond Verdicts: A Graph-Based Analysis of Human and LLM Reasoning in Scientific Fact-Checking

    Abdul Ghafoor, Muhammad Arslan Manzoor, Yufang Hou

    cs.CL · cs.AI

    Misinformation that cites legitimate papers can be especially harmful when it distorts what those studies actually report. While existing automatic fact-checking systems based on large language models (LLMs) can assess whether a model assigns an Incorrect verdict and can gen- erate explanations for that decision, they typi- cally do not indicate whether the model follows the same reasoning path as human experts or arrives at the verdict...

    arxiv.org/abs/2608.23047 · PDF

  15. 15

    The Multilingual FrameNet Corpus

    Beatrice Fiumanò, Nicolas Lazzari, Simone Paolo Ponzetto, Valentina Presutti

    cs.CL · cs.AI

    This paper introduces the Multilingual FrameNet Corpus (mFNC), a novel resource that extends the English Berkeley FrameNet corpus by collecting and harmonizing existing language-specific corpora across nine additional languages: Brazilian Portuguese, Chinese, Dutch, French, German, Italian, Korean, Latvian and Swedish. By training models that rely on different architectures on the mFNC, we consistently outperform existing state-of-the-art...

    arxiv.org/abs/2608.23037 · PDF

  16. 16

    Beyond Surface Cues: Disentangling Sociocultural Signals in Multilingual LLMs

    Yuanjun Feng, Tanzhou Liu, Stefan Feuerriegel, Yash Raj Shrestha

    cs.CL · cs.AI

    Multilingual LLM outputs can vary across sociocultural contexts. However, evidence of cultural grounding can be misleading: identity labels may be inferred from explicit or indirect textual cues, while names and wording can reveal the source language. Treating all these signals as evidence of cultural grounding may obscure potential biases. We present a human-validated, multi-agent audit that separates three questions: whether outputs...

    arxiv.org/abs/2608.23026 · PDF

  17. 17

    Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality

    Xunlei Chen, Qirui Ye, Yuang Li, Yi Gong, Zhaokun Wang, Wenyi Li, Shiyao Guo, Jinyu Guo

    cs.CL · cs.AI

    Large language models (LLMs) require effective unlearning to address privacy regulations and safety concerns. However, achieving precise forgetting without compromising general utility remains challenging. Existing sequence- and token-level methods penalize target outputs without modeling their context-dependent retrieval paths, which can disrupt linguistic structure or suppress benign knowledge. We present ADU, a fine-grained, training-based...

    arxiv.org/abs/2608.23020 · PDF

  18. 18

    What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation

    Ziyue Wang, Aomufei Yuan, Yiran Yao, Linli Yao, Hongyao Zuo, Ziwen Gong, Yuanxin Liu, Shicheng Li, Yishuo Cai, Tong...

    cs.CL · cs.AI

    Large language models are increasingly used to propose research ideas, yet the prevailing ways of judging such ideas supply no shared decision rule: free-form judging sways with style and position, and scoring against a later paper rewards recovery of one realized trajectory. We introduce a benchmark that carries a proposal from Literature to Test: the Lit2Test benchmark centers on a six-field contract organized around a falsifying outcome,...

    arxiv.org/abs/2608.22948 · PDF

  19. 19

    Do Spoken Language Models Hear Speech as They Read Text? Bridging Structural Gaps Between Speech and Text

    Hyeonyu Kim, Hwayeon Kim, Youngwon Choi, Myeongkyun Cho, Huu-Kim Nguyen

    cs.CL · cs.AI

    Spoken Language Models (SLMs) generate textual responses directly from speech, offering an alternative to cascaded systems. Despite recent advances, existing SLMs still exhibit weaker instruction-following behavior and limited generalization across diverse tasks compared to text-based language models. Our analysis shows that speech and text representations in current SLMs remain weakly aligned despite strong downstream performance, indicating...

    arxiv.org/abs/2608.22908 · PDF

  20. 20

    AraDetox: A Multi-Dialect Arabic Detoxification Dataset

    Mo El-Haj

    cs.CL · cs.AI

    Arabic harmful-language detection has received considerable attention, yet Arabic text detoxification remains underexplored. We introduce AraDetox, a multi-dialect Arabic detoxification dataset comprising 10,500 harmful social-media posts and 84,000 detoxified rewrites generated using GPT-5 and Gemini 2.5 Flash across Modern Standard Arabic, Gulf, Levantine, and Egyptian Arabic. The generated outputs were assessed through human evaluation and...

    arxiv.org/abs/2608.22894 · PDF

  21. 21

    SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Support

    Ahnaf Atef Choudhury, Ramkrishna Saha

    cs.CL · cs.AI

    Medical large language models are often judged by how many clinical questions they answer correctly. That view is useful, but it misses a practical risk. A model may know the right answer and still change its response when the same case is written in a different patient voice. This paper evaluates that risk as SDoH aware narrative anchoring bias. We use NarrativeShield SDoH MedQA, a counterfactual medical question answering dataset in which...

    arxiv.org/abs/2608.22802 · PDF

  22. 22

    TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents

    Wenhao Wu, Menghao Zhang, Xin Wang, Zhi Wang, Kun Shao, Jian Luan

    cs.CL · cs.AI

    Reliable deployment of LLM agents in user-facing products depends not on raw task-solving ability but on consistency and limit-awareness: behaving the same way across repeated trials, and recognizing when a request cannot, or cannot yet, be safely fulfilled. CAR-bench exposes this reliability gap in the domain of in-car assistants: an LLM-simulated user issues incomplete or ambiguous requests, requiring the agent to resolve uncertainty...

    arxiv.org/abs/2608.22793 · PDF

  23. 23

    Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time

    Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder, Sanjay Basu, Ravid Shwartz-Ziv

    cs.CL · cs.AI · cs.LG

    Large Language Models generate text autoregressively, but open-ended generation is prone to verbatim looping, in which models repeat spans already present in context. Standard defenses such as repetition, presence, and frequency penalties and n-gram blocking act on token recurrence rather than the sequential structure of a loop, and often suppress looping only at strengths that also degrade formatting or fluency. We propose Don't Repeat...

    arxiv.org/abs/2608.22761 · PDF

  24. 24

    XTC: Head-Aware Sampling by Excluding Top Choices

    Philipp Emanuel Weidmann, Allen Roush, Judah Goldfeder, Sanjay Basu, Ravid Shwartz-Ziv

    cs.CL · cs.AI · cs.LG

    Standard decoding rules for autoregressive language models promote diversity by rescaling the full next-token distribution or truncating its low-probability tail. These strategies overlook a common regime of open-ended generation in which several continuations are plausible but too much probability mass remains concentrated on the most generic choice. We introduce XTC (Exclude Top Choices), a lightweight head-aware decoding operator that...

    arxiv.org/abs/2608.22758 · PDF

  25. 25

    DiaRelay: Relaying Dialogue Context with a Constant-Size Memory for Emotion Recognition in Conversation

    Zihao Zhou, Bin Yang, Jinghui Qin, Kebing Jin

    cs.CL · cs.AI

    Emotion Recognition in Conversation (ERC) requires models to identify subtle emotional cues that are often distributed across distant dialogue turns. Existing methods typically incorporate dialogue history through a fixed context window. However, short windows discard potentially useful long-range evidence, while enlarging the window repeatedly re-encodes overlapping utterances, increases computational and memory costs, and may introduce...

    arxiv.org/abs/2608.22745 · PDF

This edition is part of The Daily Abstract — cs.CL archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.