cs.CL · 2026-08-28 · No. 98
Computation and Language, 2026-08-28.
12 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
12 entries-
01
How Language Models Organize and Structure Moral Knowledge
Orion Reblitz-Richardson
cs.CL · cs.AI · cs.LG
How do large language models (LLMs) organize moral knowledge? Models detect moral content broadly, but detection is a low bar. We ask whether they go further, distinguishing moral foundations from one another and organizing the relationships between them geometrically. We train six independent linear probes on open-weight language models, one per Moral Foundations Theory (MFT) category (care/harm, fair/cheat, lib/oppress, loy/betray,...
-
02
Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction
Jin Mu, Guanhua Chen
cs.CL · cs.AI
Clinical language models can achieve strong in-hospital accuracy yet fail under deployment shifts because they exploit note-specific artifacts (e.g., templates, separators, boilerplate) that do not reflect patient state. We propose CAST (Concept-guided Artifact Suppression Tuning), an SAE-based framework for auditable clinical text classification. CAST uses Sparse Autoencoders to expose sparse, human-auditable features from intermediate...
-
03
Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090
Kairong Luo, Jiarui Cui, Yaorui Yin, Shengqi Chen, Yiming Yang, Linxiang Gao, Yanmohan Wang, Mingzhe Zhang, Kaiyue...
cs.CL · cs.LG
Language model pretraining has become almost synonymous with prohibitive cost, placing it out of reach for much of the academic and open-source communities. Although strong open-source efforts already exist, including open-weight models and open-source training recipes, a cost-efficient, hardware-accessible, and open-source pretraining recipe has long been missing. Even at a small scale, training Llama-3.2-3B costs over \$1.5M, and...
-
04
RCMN: Understanding Misleadingness in Influential Public Discourse
Peiling Yi
cs.CL · cs.AI
Influential public discourse shapes public beliefs and can also mislead, not only through what is stated, but also through how information is framed, omitted, contextualised, and communicated. Yet less research has focused on how such misleadingness arises and shapes the interpretations formed by readers. To address this gap, we introduce Reader-Centric Misleadingness Understanding (RCMN), a framework that operationalises misleadingness...
-
05
Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit
Shuyi Fan, Boyuan Deng, Mengyu Xu, Xinhong Xie, Chenyang Li, Hongyang Zhang
cs.CL · cs.AI · cs.CY
Audits of LLM judges certify a bias by contrasting matched conditions, and the strongest designs difference twice: a within-item contrast between two candidate responses, differenced again across a manipulated attribute, read off a bounded rating scale. We show that this endpoint is not identified on the scale that reports it. Each term of the double difference is censored by its own share, so the observed statistic confounds differential...
-
06
When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue
Yen-Ju Lu, Yuzhe Wang, Yaohan Guan, Xiluo He, Jiarui Hai, Mingrui Liang, Kaavya Chaparala, Thomas Thebaud, Laureano...
cs.CL · cs.AI · cs.LG · eess.AS
Understanding spoken dialogue requires joint reasoning over lexical content and paralinguistic acoustic signals such as emotion and conversational intent. However, existing evaluations often allow shortcuts based on transcripts or single-modality solutions, obscuring whether models genuinely ground predictions in speech. We formalize this failure mode as cross-modal disagreement, where transcripts suggest plausible but incorrect surface...
-
07
Squeezing More from Limited Data with Recursive Transformers
Serdar Gülbahar, Lukas Edman, Alexander Fraser
cs.CL · cs.LG
Pre-training under limited data requires a different view of scaling than web-scale language modeling. With a fixed data budget but relatively abundant compute, increasing parameter count helps only up to an optimal scale; beyond that point, models overfit and generalization worsens. We study this behavior across 10M-100M word pre-training budgets, two corpora, and multiple downstream evaluations, and find that optimal size depends strongly...
-
08
Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay
Prateek Chhikara
cs.CL · cs.AI
Interactive language-model agents use confidence signals to decide whether to answer immediately, retrieve additional evidence (from memory or external knowledge), or defer. Yet confidence is usually evaluated in isolation, without measuring the trajectory-level consequences of the actions it triggers. We propose matched trajectory replay, a controlled protocol for comparing confidence-to-action mappings. The protocol holds candidate answer...
-
09
Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory
Zihao Cheng, Yingyu Shan, Hongru Wang, Zeming Liu, Xinyi Wang, Xiangrong Zhu, Yuhang Guo, Wei Lin, Yunhong Wang
cs.CL · cs.AI
Travel planning agents assist users in generating personalized travel plans by modeling their individual preferences. Existing agents either rely on explicit user instructions or engage in multi-turn clarification to elicit user preferences. However, both approaches overlook the rich behavioral signals latent in users' past behaviors, which implicitly encode their preferences. This over-reliance on active user input increases interaction...
-
10
Equal Ranking Quality, Different Decisions: Training Order-Consistent LLM Scorers
Markus Frohmann, Mahdiyar Alavi, Elizabeth Lingg, Navid Rekabsaz
cs.CL · cs.IR · cs.LG
Rerankers, reward models and multi-document QA scorers score candidate documents or responses in one LLM prompt, so each score depends on their order. Such scorers are selected on ranking quality, but their scores determine a decision: what a score threshold retains, a reader answers, or a preference model selects. However, equal ranking quality does not imply equal decisions: on passage reranking, five trained scorers within 0.010 nDCG@10...
-
11
FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Models
Junyoung Lee, Sehyeon Park, Shinhyoung Jang, Seonha Ryu, Hojeong Kim, Hyunsei Lee, Il Hong Suh, Yeseong Kim
cs.CL · cs.AI · cs.LG
Pruning is a practical approach to compress large language models (LLMs), but it can amplify text degeneration, especially repetition loops, even when perplexity and task accuracy remain largely unchanged. In this work, we present a token-level analysis of this failure mode by viewing decoding as a dynamical process that enters and persists in a small set of recurrent contexts. Our analysis decomposes degeneration into loop entry risk and...
-
12
Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference
Mengfan Li, Zesheng Wei, Xuanhua Shi, Yang Deng
cs.CL · cs.AI
As large language models are increasingly deployed to simulate diverse human characters, ensuring persona fidelity, defined as the extent to which an agent's behavior consistently reflects the psychological and stylistic characteristics of a target persona, has become a critical requirement. However, existing evaluation paradigms primarily rely on either holistic LLM-based judges, which are prone to "holistic appraisal hallucination'', or...
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.