cs.CL · 2026-06-27 · No. 36

Computation and Language, 2026-06-27.

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

01 — The papers

17 entries
  1. 01

    Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning

    Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

    cs.CL · cs.AI · cs.CV · cs.LG

    Multimodal web agents can assist humans in operating repetitive GUI tasks, where effective task planning is essential for decomposing complex tasks into executable actions. While small open source MLLMs are cost efficient and privacy preserving compared with commercial large models, they suffer from weak planning and limited cross website generalization. To address these limitations, we introduce the planning experience exploration and...

    arxiv.org/abs/2606.27330 · PDF

  2. 02

    Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts

    Zhengyuan Liu, Stella Xin Yin, Min-Yen Kan, Nancy F. Chen

    cs.CL · cs.AI

    We present a conceptual framework for analyzing dialogue in collaborative problem-solving contexts, with an emphasis on the emerging dynamics of human-AI and multi-agent collaboration. As intelligent systems become active agents capable of autonomous reasoning and strategic cooperation, understanding the dialogic interaction during collaborative problem solving is increasingly important for optimizing and evaluating such partnerships. Our...

    arxiv.org/abs/2606.27233 · PDF

  3. 03

    CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention

    Sayak Dutta

    cs.CL · cs.AI · cs.LG · cs.NE

    Recurrent models must forget in order to remember, yet the state of the art decides what to erase without consulting what is stored -- the gate sees only the arriving token, not the memory it is about to modify. This memory-blind gating is one of three coupled defects in the leading delta-rule architecture (GDN-2): the value-axis erase mask wastes parameters at the scale of the value projection, and -- as we prove -- mathematically prevents...

    arxiv.org/abs/2606.27229 · PDF

  4. 04

    Forecasting With LLMs: Improved Generalization Through Feature Steering

    Humzah Merchant, Bradford Levy

    cs.CL · cs.LG

    Successful forecasting involves identifying patterns between historical and future states of the world which generalize to future observations. We apply LLMs to a variety of forecasting tasks and inspect their internal states using sparse autoencoders to understand whether they appear to rely on time-specific pieces of knowledge versus generalizable patterns. Our analyses identify features associated with both time-aware reasoning and...

    arxiv.org/abs/2606.27199 · PDF

  5. 05

    NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models

    Henry Shaowu Yuchi, Michal Kucer, Benjamin H. Sims, Selma Peterson, Emily Taylor

    cs.CL · cs.AI

    Large language models (LLMs) have demonstrated strong performance across a wide range of tasks, but ensuring their reliability in highly technical domains remains a significant challenge. In nuclear engineering, problem solving often requires not only factual knowledge but also quantitative reasoning and conceptual understanding. To address the need for systematic evaluation in this domain, we introduce NuclearQAv2, a benchmark for assessing...

    arxiv.org/abs/2606.27047 · PDF

  6. 06

    Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs

    Sinie van der Ben, Raphaël Baur, Yannick Metz, Mennatallah El-Assady

    cs.CL · cs.AI

    Recent work identified emotion vectors in Claude Sonnet 4.5, which are internal representations that encode emotion concepts, causally influence behavior, and exhibit geometry mirroring human psychological structure. We test the generality of these findings in two open-weight models, Apertus-8B-Instruct-2509 and Gemma-4-E4B-it, extracting emotion contrast vectors across all layers, using two model-generated corpora. We recover valence...

    arxiv.org/abs/2606.26987 · PDF

  7. 07

    ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models

    Xin Lin, Liang Zhang, Guoqi Ma, Hongyao Tu, Jinsong Su

    cs.CL · cs.AI

    Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world applications. The core challenge of OpenRE lies in achieving reliable generalization to unseen relation types. Current OpenRE approaches either employ clustering techniques, which cannot generate relation labels and suffer from poor generalization, or rely on direct relation label generation via...

    arxiv.org/abs/2606.26986 · PDF

  8. 08

    Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions

    Abla Bedoui, Ashley L. Greene, Mohammed Cherkaoui

    cs.CL · cs.AI

    Large language models (LLMs) are increasingly being integrated into mental health support tools and other psychologically sensitive conversational applications. In such settings, behavioral stability and consistency are important for trustworthy human-AI interaction. However, semantically similar concerns can be presented through different contextual framings, potentially eliciting different model responses. Such framing-sensitive variability...

    arxiv.org/abs/2606.26982 · PDF

  9. 09

    SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages

    Subham Kumar, Prakrithi Shivaprakash, Abhishek Manoharan, Astut Kurariya, Diptadhi Mukherjee, Prabhat Chand, Pratima...

    cs.CL · cs.AI

    Automatic Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in multilingual and demographically diverse Indian healthcare context remains largely unknown. In this study, we first conduct the systematic audit of ASR performance on real-world psychiatric interview data spanning Kannada, Hindi and Indian English, comparing eight state-of-the-art models including IndicWhisper, WhisperLargeV3,...

    arxiv.org/abs/2606.26901 · PDF

  10. 10

    Heterogeneous Neural Predictivity from Language Models During Naturalistic Comprehension

    Xiao Jia

    cs.CL · cs.LG

    Language-model representations provide structured, high-dimensional annotations of naturalistic language stimuli and can serve as informative neural predictors during comprehension. We analyzed locked derived data from Brain Treebank, MEG-MASC, and Podcast ECoG with eight frozen language models, blocked encoding models, and matched temporal, nuisance, and representation-capacity controls. Positive held-out prediction and gains over low-level...

    arxiv.org/abs/2606.26880 · PDF

  11. 11

    Information-Aware KV Cache Compression for Long Reasoning

    Jushi Kai, Zhuiri Xiao, Alexandra Birch, Zhouhan Lin

    cs.CL · cs.AI

    Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages. Existing KV cache compression methods mainly rely on attention weights to estimate token importance. While attention effectively captures contextual relevance, it overlooks complementary information-theoretic signals related to predictive uncertainty and token informativeness....

    arxiv.org/abs/2606.26875 · PDF

  12. 12

    Evaluation Pitfalls and Challenges in Multimedia Event Extraction

    Philipp Seeberger, Steffen Freisinger, Tobias Bocklet, Korbinian Riedhammer

    cs.CL · cs.LG

    Multimedia event extraction aims to jointly identify events and their arguments across multiple modalities, such as text and images, to support more comprehensive event understanding. While recent work reports steady and substantial progress, the reliability and comparability of these results critically depend on consistent and rigorous evaluation. In this work, we present the first systematic analysis of evaluation pitfalls in multimedia...

    arxiv.org/abs/2606.26775 · PDF

  13. 13

    Beyond Logical Forms: LLM-Extracted Patterns for Fallacy Classification

    Eleni Papadopulos, Firoj Alam, Giovanni Da San Martino

    cs.CL · cs.AI

    In today's fast-paced information era, logical fallacies, defined as defective patterns of reasoning, inevitably contribute to the growth of information disorder. However, often fallacies appear in nuanced forms that complicate automated classification. In this study, we investigate whether merging abstract logical structures with context-level linguistic cues proves beneficial for fallacy classification, developing a framework that...

    arxiv.org/abs/2606.26698 · PDF

  14. 14

    CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

    Shigeng Wang, Chao Li, Yangyuxuan Kang, Jiawei Fan, Anbang Yao

    cs.CL · cs.AI

    In this paper, we present CAT-Q, Cost-efficient and Accurate Ternary Quantization, for compressing and accelerating LLMs. Unlike existing state-of-the-art ternary quantization methods that rely on data-intensive and costly quantization-aware training to mitigate severe performance degradation, CAT-Q is a simple yet effective post-training quantization scheme that is readily applicable to LLMs with diverse architectures and model sizes. It has...

    arxiv.org/abs/2606.26650 · PDF

  15. 15

    \textsc{DiARC}: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models

    Yuxuan Yang, Feiyang Li, Yile Wang

    cs.CL · cs.AI

    The Abstraction and Reasoning Corpus (ARC;~\citealp{chollet2019measure}) contains tasks that require summarizing patterns from limited grid samples and predicting output grids. Recently, many large language model based approaches have attempted to transform it into a text-based reasoning task. However, methods based on open-source models have generally yielded unsatisfactory results, while those relying on closed-source models are too costly....

    arxiv.org/abs/2606.26530 · PDF

  16. 16

    The Inattentional Gap: Task-Conditioned Language and Vision Models Omit the Safety-Critical Signals They Can Otherwise Report

    Kwan Soo Shin

    cs.CL · cs.AI · cs.CV

    AI safety is evaluated by how reliably a model detects the hazards it is told to find, yet accidents often arise from the hazard no one specified. We show that conditioning a language or vision model on a narrow task suppresses its reporting of co-present, safety-critical signals it can otherwise report, a machine analogue of human inattentional blindness arising from a different mechanism. Across radiology and driving text scenarios and...

    arxiv.org/abs/2606.26529 · PDF

  17. 17

    Temporal Validity in Retrieval Memory: Eliminating Stale-Fact Errors for AI Agents over Evolving Knowledge

    Neeraj Yadav

    cs.CL · cs.AI · cs.ET · cs.LG

    Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time. When a fact changes (e.g., a function is renamed or API restructured), RAG retrieves both the stale and current value with near-identical embedding similarity. The agent then either abstains or serves the superseded fact. We show this is a structural problem: on a calibrated dataset, cosine similarity distinguishes a contradicted fact...

    arxiv.org/abs/2606.26511 · 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.