cs.CL · 2026-07-01 · No. 40

Computation and Language, 2026-07-01.

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

01 — The papers

14 entries
  1. 01

    Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision

    Zifan Carl Guo, Laura Ruis, Jacob Andreas, Belinda Z. Li

    cs.CL · cs.AI · cs.LG

    When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation? We study LMs trained to explain which features of their inputs influenced their behavior, using models' counterfactual behavior on modified inputs as supervision. Surprisingly, we find that LMs trained on fixed counterfactual explanations derived from earlier checkpoints of themselves, or even...

    arxiv.org/abs/2606.32038 · PDF

  2. 02

    Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

    Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona, Idan Szpektor, Arman Cohan

    cs.CL · cs.AI

    Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in key metacognitive faculties: they hallucinate with high confidence, fail to recognize knowledge boundaries, and misrepresent their internal uncertainty--undermining trustworthiness and reliability. Since monitoring task performance and adapting behavior accordingly...

    arxiv.org/abs/2606.32032 · PDF

  3. 03

    When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

    Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

    cs.CL · cs.AI

    While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understanding the table structure. Beyond final-answer accuracy, DREs directly compromise the correctness and reliability of intermediate reasoning steps. Yet prior studies have only offered limited, small-scale analyses. In this work, we present the first systematic...

    arxiv.org/abs/2606.32029 · PDF

  4. 04

    Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors

    Mark Oskin

    cs.CL · cs.LG

    A transformer's feed-forward (FFN) sublayer materializes the distinctions attention gathers, yet gives no account of what it computes. In a parameter-neutral replacement, each hidden unit is an explicit fuzzy set operation on sigmoid-bounded [0,1] memberships: intersection A*B and set-difference A*(1-B), the latter a bounded positive negation ("A but not B") that gated/bilinear units lack -- a negation-capable FFN (NC-FFN). On N-bit parity...

    arxiv.org/abs/2606.31845 · PDF

  5. 05

    CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield

    Dohyeon Kwon, Youngjin Park

    cs.CL · cs.AI

    We study three complementary techniques for training compute-efficient language models. (1) Selective supervision and per-token efficiency. Selective Ground Truth Token Training (SGT) concentrates supervision on the ~15% of output tokens that carry semantic payload. Through positive gradient coupling in position-shared transformer weights -- a token-level instance of auxiliary-task transfer -- the remaining 85% of unsupervised tokens still...

    arxiv.org/abs/2606.31796 · PDF

  6. 06

    STEB: Style Text Embedding Benchmark

    Rafael Rivera Soto, Anna Wegmann, Cristina Aggazzotti

    cs.CL · cs.AI · cs.LG

    While semantic embeddings are rigorously evaluated on the Massive Text Embedding Benchmark, the evaluation of style embeddings remains fragmented, with each work relying on their own set of tasks and datasets. To bridge this gap, we introduce the Style Text Embedding Benchmark, a comprehensive open-source benchmark intended to standardize the evaluation of style embeddings. STEB encompasses 96 datasets across 7 languages, spanning...

    arxiv.org/abs/2606.31741 · PDF

  7. 07

    Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue

    Nan Li, Albert Gatt, Massimo Poesio

    cs.CL · cs.AI

    In collaborative dialogue, shared perception does not guarantee shared interpretation. Mutual understanding must be established through interaction. We investigate whether vision-language models (VLMs) can distinguish what could be shared from what has been shared between dialogue participants through grounding. We formulate this as an interpretation-matching task on 13,077 annotated reference expressions from HCRC MapTask dialogues, and...

    arxiv.org/abs/2606.31719 · PDF

  8. 08

    Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian

    Dragos-Mitrut Vasile, Elena-Simona Apostol, Stefan-Adrian Toma, Adrian Paschke, Ciprian-Octavian Truica

    cs.CL · cs.AI

    Relation extraction (RE) for low-resource languages is typically constrained by the lack of annotated corpora. We investigate the feasibility of cross-lingual RE for Romanian by combining automatic dataset translation with large language model (LLM) inference. We translate the SemEval-2010 Task 8 benchmark from English to Romanian using an LLM-based translation pipeline and evaluate Gemma 4 31B under zero-shot, few-shot, and QLoRA fine-tuned...

    arxiv.org/abs/2606.31718 · PDF

  9. 09

    FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents

    Muhammad Usman Safder, Ayesha Gull, Rania Elbadry, Fan Zhang, Yankai Chen, Xueqing Peng, Xue, Liu, Preslav Nakov, Zhuohan Xie

    cs.CL · cs.AI

    Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized with explicit behavioral mandates such as "preserve capital" or "avoid speculative bets" that are meant to govern every decision throughout deployment. In practice, however, as market context accumulates over long horizons, these mandates gradually lose their behavioral influence, a phenomenon we formalize as Mandate Salience Decay (MSD). To...

    arxiv.org/abs/2606.31522 · PDF

  10. 10

    Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics

    Kyomin Hwang, Hyeonjin Kim, Hyunho Lee, Nojun Kwak

    cs.CL · cs.AI

    Recent advances in Large Language Models (LLMs) have motivated their adoption across a wide range of domains, including Artificial Intelligence (AI) for mental health. Given the growing prevalence of mental health disorders worldwide and the limited accessibility of professional care, there is an increasing demand for scalable computational approaches that can assist in early detection and continuous monitoring of psychological well-being. In...

    arxiv.org/abs/2606.31464 · PDF

  11. 11

    Linguistic Bias Mitigation for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck

    Anh-Tuan Dao, Driss Matrouf, Mickael Rouvier, Nicholas Evans

    cs.CL · cs.LG

    Rapid advancements in generative speech technology have compromised the reliability of voice biometrics. While current spoofing detectors excel when assessed under in-domain conditions, generalisation to out-of-domain settings is often poor. We show that this can be due to linguistic bias. A reliance on linguistic cues observed in training data can then compromise robustness to cross-data. We propose a linguistic-invariant spoofing detection...

    arxiv.org/abs/2606.31411 · PDF

  12. 12

    Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law

    Noah Scharrenberg, Chang Sun

    cs.CL · cs.AI

    Large language models (LLM) trained on web-scale corpora generate output that may infringe copyright, yet existing technical safeguards focus narrowly on verbatim memorisation. EU copyright doctrine applies a broader standards: substantial similarity, which extends to stylistic choices, narrative structure, and creative elaboration. This mismatch between what current methods detect and what the law protects leaves a significant compliance...

    arxiv.org/abs/2606.31250 · PDF

  13. 13

    Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?

    Jongchan Choi, Nari Yang, Sung Soo Park, Jaemin Cho, Han Seoyoung, Haerin Shin, Jun-Hyung Park

    cs.CL · cs.AI · cs.LG

    As large language models (LLMs) are increasingly deployed as moral advisors and agents, they need to address dilemmas between two competing values. However, existing research on LLMs with moral dilemmas overlooks a central aspect of human moral cognition: the ability to imagine alternatives that move beyond the given options. We introduce MoralAltDataset, a dataset of 307 moral dilemmas spanning narrative Advisor dilemmas and AI-facing Agent...

    arxiv.org/abs/2606.31213 · PDF

  14. 14

    Gated Multi-Graph Fusion via Graph Attention Networks for Alzheimer's Disease Detection

    Jinyu Li, Xiao Wei, Bin Wen, Kai Li, Yuqin Lin, Xiaobao Wang, Longbiao Wang, Jianwu Dang

    cs.CL · cs.AI

    Spontaneous speech is a vital non-invasive biomarker for Alzheimer's Disease (AD), yet many systems overlook non-linear structural disruptions and clinical heterogeneity in pathological language. We propose a Multi-View Gated Graph Attention Network that transcribes audio via Automatic Speech Recognition (ASR) to construct semantic, dependency, and co-occurrence graphs, characterizing speech through a "content-structure-flow" framework....

    arxiv.org/abs/2606.31186 · 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.