cs.CL · 2026-06-23 · No. 32
Computation and Language, 2026-06-23.
11 new papers in cs.CL. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
11 entries-
01
War in the Abstract: The Rise and Consequences of Militarized Language in Scientific Communication
Sovesh Mohapatra, David Lydon-Staley, Dani S. Bassett
cs.CL · cs.AI · cs.CY · cs.DL
Scientists do not, by profession, wage war. Yet warfare's vocabulary consistently appears in their abstracts. To quantify the extent to which warfare's vocabulary pervades scientific abstracts, we analyze 21.4 million papers (2010-2025; OpenAlex, PubMed). We additionally run a within-subject war-framing experiment (N = 801; 32,040 trials) designed to provide causal insight into the effects of militaristic language on persuasion. Between 2010...
-
02
UnBias-Plus: Detect, Explain, and Rewrite Bias
Ahmed Y. Radwan, Ahmed ElKady, Sindhuja Chaduvula, Mohamed Hafez, Amrit Krishnan, Shaina Raza
cs.CL · cs.AI · cs.SE
Bias in natural language remains a persistent challenge in both human-written and AI-generated content, affecting domains such as journalism, education, and AI research. Most existing detection methods identify only the presence of bias, with limited support for granular detection, interpretable explanations, neutral rewriting, and openly available trained models. We present UnBias-Plus, an open-source toolkit unifying (1) segment-level...
-
03
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
Jun Zhang, Jiasheng Zheng, Boxi Cao, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun
cs.CL · cs.AI
The emergence of Large Reasoning Models has introduced exceptionally long Chain-of-Thought traces, creating a transparency burden where critical logic is often buried under massive procedural text. To address this, we present ReasoningLens, an open-source framework designed for the hierarchical visualization and diagnostic auditing of complex reasoning chains. ReasoningLens addresses information necropsy by: (1) structuring traces into...
-
04
Energy-Based Transformers as Predictors of Reading Difficulty
Jakub Dotlacil, Ece Takmaz
cs.CL · cs.AI
Transformer language models have become established tools for modeling human sentence processing, with measures such as surprisal and attention entropy serving as effective predictors of reading difficulty that together capture complementary aspects of processing load. Here, we explore a related class of transformer models: energy-based transformers, which provide a principled formal link to associative memory models, bringing processing...
-
05
Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
Arthur Wuhrmann, Gaetan Stein, Daniel Brunner, Andrei Kucharavy
cs.CL · cs.AI
While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow uses with well-understood and mitigated risks have emerged. Notably the Swiss Federal Supreme Court uses small on-premises models for tentative translations and short-passage summarization across the four official languages. However, such usage is challenging in the context of Criminal Law. Since rulings...
-
06
The Anatomy of the CTC Oracle Gap: Acoustic Exhaustion and Linguistic Recovery
Ivan Novosad
cs.CL · cs.LG
We study the limits of CTC-internal scoring for N-best hypothesis selection and locate the information bottleneck separating acoustic confidence from linguistic plausibility. Eleven CTC-internal and acoustic-feature scoring strategies produce no statistically significant WER improvement over greedy decoding on LibriSpeech dev-other at G=16 (all p > 0.05). The exhaustion is systematic: CTC's Spearman $ρ$ between hypothesis score and...
-
07
MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations
Elena Sofia Ruzzetti, Cornelius Emde, Sangdoo Yun, Seong Joon Oh, Martin Gubri
cs.CL · cs.AI
LLM agents are increasingly deployed in multi-party environments, handling sensitive personal data on behalf of individual users, for instance in group chats. When such an agent discloses private information, it reaches every group member at once. This risk is structurally harder to control than in one-to-one settings, as every piece of private information must be appropriate for every recipient in the group. Yet all existing contextual...
-
08
When Does Intrinsic Self-Correction Help? A Task-Sensitive Analysis
Elroy Stav, Dvir Berlowitz, Maayan Orner, Sarit Kraus
cs.CL · cs.AI
Intrinsic self-correction (SC) aims to improve large language model outputs by prompting a model to revisit its own initial answer without external feedback. Recent studies have questioned the reliability of this approach, showing that models often struggle to judge whether their initial responses are correct. In this work, we take a task-sensitive view of SC. Rather than asking whether it works in general, we examine settings where SC may...
-
09
PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation
Jiaqiang Wu, Zhouan Zhu, Shangfei Wang
cs.CL · cs.AI
Large language models have demonstrated significant capabilities in generating diverse and context-aware responses for empathetic dialogue. However, their computational demands severely limit their deployment in resource-constrained environments. While knowledge distillation offers a promising compression solution, it often fails to transfer the nuanced understanding essential for empathy, as it overlooks the implicit contextual cues that...
-
10
Training Open Models for Agentic Phone Use
Zhengyang Tang, Xin Lai, Pengyuan Lyu, Xinyuan Wang, Tianyi Bai, Chenxin Li, Yiduo Guo, Huawen Shen, Yuxuan Liu,...
cs.CL · cs.AI
Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult because the environment that matters at deployment, real devices running real apps, is slow, stateful, side-effectful, and hard to reset or verify, while scalable mock environments only approximate real behavior. We present PhoneBuddy, a training recipe and open-model line for agentic phone use that...
-
11
StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMs
Youxin Zhu, Yixuan Ding, Peng Lai, Longyue Wang, Bingyi Jing, Guanhua Chen
cs.CL · cs.AI
Statistical analysis is a broad, complex field requiring both domain knowledge and tool proficiency. While prior work has evaluated large language models (LLMs) in this domain, existing benchmarks remain limited in scope and format. To bridge this gap, we introduce StatABench (Statistical AnalysisBenchmark), a benchmark designed to systematically assess LLMs' statistical analysis capabilities. StatABench comprises two complementary...
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.