cs.CL · 2026-06-02 · No. 13

Computation and Language, 2026-06-02.

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

01 — The papers

18 entries
  1. 01

    From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression

    Elia Cunegatti, Marcus Vukojevic, Erik Nielsen, Giovanni Iacca

    cs.CL · cs.AI

    Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules. Existing replacement-based methods share two design constraints: full-layer granularity and contiguous selection. We argue that this is overly restrictive: in fact, redundancy in pretrained transformers is not confined to contiguous regions, nor does it evenly distribute between...

    arxiv.org/abs/2606.02559 · PDF

  2. 02

    SimSD: Simple Speculative Decoding in Diffusion Language Models

    Junxia Cui, Haotian Ye, Runchu Tian, Hongcan Guo, Jinya Jiang, Haoru Li, Chaojie Ren, Yiming Huang, Kaijie Zhu,...

    cs.CL · cs.AI

    Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding. However, their masked language modeling formulation remains incompatible with standard token-level speculative decoding, one of the most effective acceleration techniques for AR models. In AR decoding, the causal mask preserves temporally valid token-level...

    arxiv.org/abs/2606.02544 · PDF

  3. 03

    Learning When to Translate for Multilingual Reasoning

    Deokhyung Kang, Hyounghun Kim, Gary Geunbae Lee

    cs.CL · cs.AI

    Reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, but still exhibit substantial multilingual reasoning gaps, largely due to language-understanding failures in non-English inputs. English translation can mitigate these failures by expressing non-English inputs in a form that RLMs can more reliably interpret, yet translating every input is unnecessary when the model can reason reliably from the original...

    arxiv.org/abs/2606.02465 · PDF

  4. 04

    PaSBench-Video: A Streaming Video Benchmark for Proactive Safety Warning

    Yusong Zhao, Yuejin Xie, Youliang Yuan, Junjie Hu, Jitian Guo, Yujiu Yang, Pinjia He

    cs.CL · cs.AI · cs.CV

    Between the first visible sign of danger and the moment an accident occurs, there is often a window where intervention remains possible. Video-capable multimodal large language models (MLLMs) could serve as always-on safety monitors that issue warnings during this window. Yet current benchmarks do not test this ability: they rely on static inputs, ignore timing precision, and omit false-positive measurement on safe scenes. We present...

    arxiv.org/abs/2606.02443 · PDF

  5. 05

    Investigating and Alleviating Harm Amplification in LLM Interactions

    Ruohao Guo, Wei Xu, Alan Ritter

    cs.CL · cs.LG

    Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm amplifiers that enable malicious users to achieve harmful outcomes beyond their capabilities through extended interactions. This risk manifests along two axes, i.e., democratizing domain expertise that allows novices to produce specialized harmful content, and scaling harmful operations at volumes that manual effort cannot match. Existing...

    arxiv.org/abs/2606.02423 · PDF

  6. 06

    AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis

    Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi, Paul Flanagan, Oisín Redmond, Joao Bettencourt-Silva, Gurdeep...

    cs.CL · cs.AI

    Systematic reviews rely on forest plots to synthesise quantitative evidence across biomedical studies, but generating them remains a fragmented and labour-intensive process. Researchers must interpret complex clinical texts, manually extract outcome data from trials, define appropriate interventions and comparators, harmonise inconsistent study designs, and carry out meta-analytic computations-typically using specialised software that demands...

    arxiv.org/abs/2606.02403 · PDF

  7. 07

    SPADE-Bench: Evaluating Spontaneous Strategic Deception in Agents via Plan-Action Divergence

    Yuyan Bu, Haowei Li, Qirui Zheng, Bowen Dong, Kaiyue Yang, Jiaming Ji, Yingshui Tan, Wenxin Li, Yaodong Yang, Juntao Dai

    cs.CL · cs.AI

    As LLM-based agents expand their operational scope, reliability becomes a prerequisite for real-world deployment. However, in practical applications, human users cannot monitor every immediate behavior; instead, the execution process often remains a black box, leaving users dependent solely on the agent's self-reported updates. This opacity creates a critical risk: agents may present observer-facing reports that diverge from their executed...

    arxiv.org/abs/2606.02380 · PDF

  8. 08

    Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025

    Maria Kunilovskaya, Gagan Bhatia, Lisa Sophie Albertelli, Yanran Chen, Christian Greisinger, Lotta Kiefer, Christoph...

    cs.CL · cs.AI

    Human annotation is the empirical foundation of much NLP research, from dataset construction to model evaluation, but papers often leave unclear who produced the annotations and how the annotation process was controlled. We provide the first large-scale, task-level audit of human annotation reporting across major NLP venues, asking which annotation details are documented, which are missing, and how reporting varies across time, topic, venue,...

    arxiv.org/abs/2606.02255 · PDF

  9. 09

    Consistency Training while Mitigating Obfuscation via Rate Matching

    Sohaib Imran, Prakhar Gupta, Jannes Elstner, David Demitri Africa

    cs.CL · cs.AI

    Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer. Consistency training reduces this influence by training models to behave similarly across inputs with and without the extraneous feature. However, existing methods train for consistency over entire responses or internal activations, which also constrains whether the model verbalises said extraneous features. We show this...

    arxiv.org/abs/2606.02211 · PDF

  10. 10

    Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages

    Saeed Almheiri, Bilal Elbouardi, Salsabila Zahirah Pranida, Irina Nikishina, Ashwath Rao B, Parameswari...

    cs.CL · cs.AI

    Idiomatic expressions pose a major challenge for multilingual NLP because their meanings shift between figurative and literal usage, often requiring context for accurate interpretation. Prior work has focused on high-resource languages typically evaluates isolated idiom-meaning questions, overlooking realistic discourse. We introduce MIDI, a multilingual idiom dataset spanning 3 high-, 3 medium-, and 12 low-resource languages, curated by...

    arxiv.org/abs/2606.02147 · PDF

  11. 11

    A Primer in Post-Training Reasoning Data: What We Know About How It Works

    Yaoming Li, Guangxiang Zhao, Qilong Shi, Lin Sun, Xiangzheng Zhang, Tong Yang

    cs.CL · cs.AI

    Post-training has become a primary driver of recent progress in large reasoning models, and reasoning data are often the key variable determining whether this stage succeeds. Work on post-training reasoning data has grown rapidly, yet this literature remains scattered across dataset papers, reinforcement-learning recipes, reward-model studies, benchmarks, and frontier system reports. This paper is the first primer to synthesize over 150 key...

    arxiv.org/abs/2606.02113 · PDF

  12. 12

    The Role of Ambiguity in Error Prediction via Uncertainty Quantification

    Ieva Raminta Staliūnaitė, James Bishop, Andreas Vlachos

    cs.CL · cs.AI · cs.LG

    The task of Error Prediction, namely predicting whether a model output is correct, is commonly tackled with Uncertainty Quantification (UQ). However, while uncertainty metrics capture when models lack knowledge or capacity to make a prediction, they also reflect aleatoric uncertainty, which is inherent in the model input and context. This paper presents a method for improving error prediction for Large Language Models (LLMs), by disentangling...

    arxiv.org/abs/2606.02093 · PDF

  13. 13

    Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning

    Ting Xu, Xu He, Yupu Lu, Jiankai Sun, Dong Li, Wai Lam, Jianye Hao

    cs.CL · cs.LG

    This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence. We demonstrate that the Confidence Region possesses two critical properties: 1) High Reliability -- answers in the confidence region become highly accurate and stable, and 2) High Redundancy -- models generate unnecessary tokens...

    arxiv.org/abs/2606.02020 · PDF

  14. 14

    PlanarBench: Evaluating LLM Spatial Reasoning via Planar Graph Drawing

    Oleksandr Nikitin

    cs.CL · cs.AI

    PlanarBench tests whether LLMs can draw planar graphs as ASCII art given only an edge list -- a spatial reasoning task that resists memorization because edge order, edge orientation, and node labels are all permutable. We evaluate 91 models on the 199 simplest non-isomorphic connected planar graphs (2 - 7 vertices). Edge count is the dominant difficulty predictor ($r = -0.85$) -- a finding not reported in prior LLM graph benchmarks, which use...

    arxiv.org/abs/2606.02010 · PDF

  15. 15

    Machine Learning for Coding Retail Product Names to Consumer-Price Categories: A Rule-plus-Bag-of-Words Pipeline with Reliability-Weighted Human-in-the-Loop Labeling

    Vladimir Beskorovainyi

    cs.CL · cs.LG

    Consumer-price measurement increasingly draws on alternative data sources -- scanner, web-scraped, and transaction/receipt data. A recurring obstacle is that product descriptions in such sources are short, noisy, and abbreviated, with no standard product code, so each item must first be mapped to a consumption classification (e.g., the UN COICOP scheme) before prices can be compared. This paper studies that mapping as a general, reproducible...

    arxiv.org/abs/2606.02004 · PDF

  16. 16

    MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?

    Xinyu Che, Junqi Xiong, Yunfei Ge, Xinping Lei, Shihao Li, Hang Yan, Han Li, Yuanxing Zhang, Zhiqi Bai, Jinhua Hao,...

    cs.CL · cs.AI · cs.LG

    Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks. However, such knowledge is often multimodal, heterogeneous, noisy, and implicitly assumes human executors, making it difficult to use directly as the skills required by agents. To bridge the gap between human-oriented guides and agent-executable skills, we formalize this problem as guide-to-skill learning: converting in-the-wild guides...

    arxiv.org/abs/2606.01993 · PDF

  17. 17

    Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time

    Mingkuan Zhao, Yide Gao, Wentao Hu, Suquan Chen, Tianchen Huang, Zhenhua An, Zetao Chang, Xiayu Sun, Yuheng Min

    cs.CL · cs.LG

    Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations. Existing mitigation strategies primarily rely on suppressing specific neuron activations or employing computationally expensive contrastive decoding mechanisms, which often result in increased perplexity or significantly elevated inference...

    arxiv.org/abs/2606.01923 · PDF

  18. 18

    KliniskVestBERT: BERT Model Specialised to Norwegian Clinical Texts

    Christian Autenried, Cosimo Persia

    cs.CL · cs.AI

    The increasing application of Natural Language Processing (NLP) in healthcare demands language models specifically attuned to the complexities of clinical language. This work introduces KliniskVestBERT, a suite of three BERT-based encoder models pre-trained on a substantial corpus of real-world, de-identified Norwegian clinical texts from Helse Vest. We continue pretraining existing language models Nb-BERT-large, NorBERT3-large, and...

    arxiv.org/abs/2606.01904 · 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.