cs.CL · 2026-10-27 · No. 155
Computation and Language, 2026-10-27.
8 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
Learning When to Commit: Schedule Distillation for Fast Diffusion Language Models
Aidar Myrzakhan, Zhiqiang Shen
cs.CL · cs.AI · cs.LG
Diffusion large language models (dLLMs) can generate multiple tokens in parallel, but often require many decoding rounds to complete a response. Efficient generation depends not only on which tokens are easy to predict, but also on how committing to them helps predict the remaining positions. A highly predictable token may provide little useful context, while revealing a less predictable token can help several other positions become...
-
02
Adapting LLM-SC to Living Sacred Heritage: Domain-Specific Extraction, Semantic Networks and Human Evaluation on Pashupatinath Temple Reviews
Hari Sitaula, Manish Sakhakarmy, Pujan Pant, Sagar Newpane
cs.CL · cs.AI
Large language model (LLM) pipelines can turn visitor reviews into structured data, but generic schemes may miss rituals, sacred spaces, cultural restrictions and emotionally mixed experiences at living sacred heritage sites. We adapted the LLM-Social Computing (LLM-SC) framework to Pashupatinath Temple, Nepal, by specifying a 12-type entity taxonomy (four original LLM-SC types plus eight sacred-heritage types), four relation types and nine...
-
03
Making Reasoning Visible: Configuration-Aware Diagnostic Modeling for Adaptive Scaffolding in Structured Reasoning Tasks
Trystan Geoffre, Zheng Yuan, Thierry Geoffre
cs.CL · cs.AI · cs.LG
Modeling the latent, multi-step reasoning processes of learners is a core challenge for adaptive tutoring systems, which often rely on simple right/wrong answers rather than understanding how students think. Instantiated here for grammatical reasoning, this study introduces a diagnostic framework that makes students' step-by-step problem-solving visible by analyzing their action sequences in an interactive learning game. The framework...
-
04
Beyond Words Alone: Disentangling Distributed Evidence for Visually Grounded Cultural Translation
Dingming Li, Yiwen Qiu, Linjuan Wu, Hongxing Li, Zixuan Wang, Xinze Lyu, Ye Guo, Daoxin Zhang, Zhe Xu, Weiming Lu,...
cs.CL · cs.AI · cs.CV
Social media enables cross-lingual communication, yet the meaning of user-generated content (UGC) is often distributed across text, images, and cultural knowledge, making translation challenging. Existing evaluations typically treat images as optional and assume textual information is sufficient, obscuring whether errors stem from missing visual evidence or inadequate cultural adaptation. We introduce \textbf{Culture-MMT}, a diagnostic...
-
05
The Geometry of Emotion Representations Across Scale, Depth, and Instruction Tuning
Adam Hollowell
cs.CL · cs.LG
We measure the emotion geometry of six LLMs spanning Google's Gemma 2 family. Using an extraction pipeline established by Sofroniew et al. (2026) on Claude Sonnet 4.5 and replicated by Hollowell (2026) on Gemma 2 27B base, we compare emotion geometry across base and instruction-tuned variants of Gemma 2 2B, 9B, and 27B. First, all six model cells exhibit the core emotion geometry. A linear map fit between two cells places held-out emotions...
-
06
Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance
Ngoc Trinh Hung Nguyen, Alonso Silva, Armen Aghasaryan, Mehwish Alam
cs.CL · cs.AI
Constrained decoding guarantees that Large Language Models (LLMs) produce outputs conforming to predefined formats, but is often assumed to inherently degrade reasoning. We examine this assumption through a taxonomy of three constraint types: \emph{format constraints}, which enforce output structure; \emph{validity constraints}, which mask invalid answer; and \emph{reasoning constraints}, which restrict reasoning trajectories. We...
-
07
Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models
Zikai Zhou, Jiacheng Sang, Yilin Xu, Yufei Jin, Monica S. Lam
cs.CL · cs.AI
A fundamental challenge for explainable and accountable language models is revealing how external information influences their answers. This paper examines whether models are self-attributive: that is, whether they indicate when -- and only when -- their responses to questions are influenced by information provided alongside the question. Furthermore, we explore how self-attribution can be improved through counterfactual training, which...
-
08
CoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems
Yujia Zheng, Tianhao Li, Shangzhi Xu, Yuekai Huang, Ziyou Jiang, Zhaoyang Li, Yuyao Ge, Junran Peng, Mingyang Li
cs.CL · cs.AI · cs.CR
Agent Skills allow LLM agents to combine reusable capabilities, but checking each Skill in isolation cannot rule out policy violations when they are composed. We term such failures Conflict of Skills (CoS): artifacts or assessment signals produced for one purpose may be reused downstream without preserving the restrictions or authorization needed for their new use. Using controlled executions of publicly available Skills and matched...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.