Computation and Language

Papers filed under cs.CL on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

16,501 to 16,560 of 19,020

A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation
Rahul Khedar, Eshita, Sneha Teja Sree Reddy Thondapu +6
cs.AIcs.CLarXiv:2609.08592v12026
EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion
Ruijie Jian, Benlei Cui, Ting Ma +8
cs.CLarXiv:2608.27844v12026
Text Restoration of Ancient Documents with Language Models
Shibingfeng Zhang, Edoardo Caraffa, Annafelicia Zuffrano +2
cs.CLcs.AIarXiv:2608.28170v12026
OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding
Gengxu Li, Yuan Wu, Yi Chang
cs.CLarXiv:2608.30678v12026
When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models
Gnaneswar Villuri, Hashmath Shaik, Alex Doboli
cs.CLcs.AIarXiv:2609.04582v12026
PACE: Publisher-Adaptive Content Extraction via Agentic Automation
Zhanlin Liu, Munirathnam Srikanth
cs.CLcs.AIarXiv:2608.27466v12026
Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning
Kevin Du, Alexander Hoyle, Laura Ruis +1
cs.CLcs.LGarXiv:2609.04194v12026
Editable Visual Design
Junyan Ye, Wei Liu, Dongzhi Jiang +9
cs.CVcs.CLarXiv:2609.04034v12026
Reliability Challenges in Diffusion Vision-Language Models
Md. Atabuzzaman, Chris Thomas
cs.CVcs.CLarXiv:2609.01318v12026
The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing
Chenguang Wang, Ming Li, Adebayo Braimah +6
cs.AIcs.CLarXiv:2609.07713v12026
UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering
Mohammad Arvan, Hossein Haeri, Natalie Parde +1
cs.CLcs.AIcs.HCarXiv:2608.27467v12026
Distinguishing Revision and Delayed Elaboration in Incremental Narrative Interpretation
Yi-Chun Chen
cs.CLcs.AIcs.MMarXiv:2608.21364v12026
AraMS-28k: The Largest Publicly Released Line-Level Dataset of Historical Arabic Manuscripts with Margin and Insertion-Anchor Annotations
Mohamed Guechaoui, Mohamed Diaa Zellagui, Souleyman Chaib +1
cs.CVcs.CLarXiv:2608.26921v12026
Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry
Alexandru-Iulius Jerpelea
cs.CLarXiv:2608.26887v12026
Research Design Tracking and Assessment for the Social Sciences
Marco Rovera, Sergiu Burlacu, Dominique Cappelletti +5
cs.CLcs.CYarXiv:2608.27049v12026
Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking
Siyu Chen, Haoran Wang, Xiaojian Li +3
cs.CLcs.AIarXiv:2609.02414v12026
Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation
Yixuan Liu, Lin Chen, Zhuoqi Liu +2
cs.DLcs.CLcs.CYarXiv:2609.01432v12026
Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations
Bo-Han Feng, Chien-Feng Liu, Yu-Hsuan Li Liang +9
cs.SDcs.AIcs.CLarXiv:2510.16893v12025
How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation
Elitsa Yotkova, Violeta Kastreva, Petar Velkov +4
cs.CLarXiv:2609.01369v12026
MedUAG: Unified Understanding and Generation for Medical Multimodal Models
Zijie Meng, Yuncheng Zhang, Hualiang Wang +8
cs.CLcs.AIarXiv:2608.18937v12026
Reinforcement Learning for improving Large Language Models' Catalan text simplification capabilities
Arnau Ayguadé Domingo, Stefan Bott, Horacio Saggion
cs.CLcs.AIarXiv:2609.04823v12026
Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Registered Negative Result
Christos Koutsiaris
cs.CLcs.AIcs.IRarXiv:2608.28151v12026
A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models
Yikai Zhao, Saurabh Pandey, Pradeep Kumar Misra
cs.CLarXiv:2609.02054v12026
Using Poly-Encoders for Computationally Efficient Automated Creativity Assessment
Sam Grouchnikov, Phillip Gregory, Jiho Noh
cs.CLcs.AIarXiv:2608.26165v12026
SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning
Michal Podstawski
cs.LGcs.CLarXiv:2608.26132v12026
Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation
M P V S Gopinadh
cs.CLcs.AIcs.CRarXiv:2608.18164v12026
DTOC: Dynamic Tool Output Compression for Adaptive Context Management in AI Agents
Abhay Chaturvedi, Shreya Bhattacharya, Rashmika Gopalkrishnan +1
cs.AIcs.CLcs.MAarXiv:2609.26121v12026
Provenance Before Prose: Claim-Locked Reporting
Xiao Fan, Jingyuan Li, Hongbin Guo +2
cs.CLarXiv:2608.25336v12026
LLM-Derived Preference Judgments Are Not Self-Consistent
Matthew T. Ford, Francis Bahk, Jingjing Wang +4
cs.AIcs.CLarXiv:2608.17644v12026
Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting
Weibin Cai, Reza Zafarani
cs.CLcs.IRarXiv:2608.25115v12026
Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs
Deniz Bayazit, Badr AlKhamissi, Antoine Bosselut
cs.CLcs.AIcs.LGarXiv:2609.00155v12026
EgoArgus: Benchmarking VLMs as Situational Assistants for Modality-Grounded User Supports
Yu-Chien Tang, Yu-Hsiang Liu, An-Zi Yen
cs.CLarXiv:2608.25561v12026
STAGEET: Stage-wise Typed Edit Tagging for Grammatical Error Correction with Arabic as a Case Study
Wenjie Lou, Alaa Mamdouh Akef
cs.CLcs.AIarXiv:2608.28614v12026
The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence
Genpei Zhang
cs.CVcs.CLcs.LGarXiv:2609.00868v12026
Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprinting
Bo Chen
cs.CLarXiv:2608.29930v12026
Evaluating AI Generated Summaries for Cancer Patients
Muhammad Aurangzeb Ahmad, Kim Shyu, Leon Oliver +2
cs.CLcs.AIarXiv:2608.26154v12026
Dr. Claw: An AI Scientist Workspace for Vibe Research
Dingjie Song, Hanrong Zhang, Dawei Liu +10
cs.AIcs.CLcs.CVarXiv:2609.00365v12026
Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models
Jungseob Lee, Seongtae Hong, Dongyub Jude Lee +4
cs.AIcs.CLcs.CVarXiv:2609.00355v12026
GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments
Lin Fu, Zheyuan Yang, Tianhui Zhang +5
cs.CLcs.AIarXiv:2609.00048v12026
Personalized Auto-Research: Towards a True AI Co-Scientist
Bo Ni, Franck Dernoncourt, Hongjie Chen +5
cs.AIcs.CLarXiv:2608.14881v12026
Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts
Jaehee Kim, Ji Hoon Chung, Seoyoon Park +5
cs.CLarXiv:2608.30270v12026
Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts
Athulith Paraselli, Etha Tianze Hua, Ellie Pavlick
cs.CLarXiv:2609.00293v12026
Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters
Bernardo Modenesi, Jody Lin, Kimberly Kaphingst +4
cs.CLcs.AIcs.LGarXiv:2608.14792v12026
How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution
Vedant Palit, Florent Draye, Terry Jingchen Zhang +2
cs.CLcs.LGarXiv:2608.27510v12026
The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure
Kaiqiao Han, Yizhou Sun
cs.CLcs.LGarXiv:2608.25005v12026
The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines
Prabhjot Singh, Bhushan Pawar
cs.AIcs.CLcs.MAarXiv:2608.14588v12026
The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding
Gilad D. Landau, Dulhan Jayalath, Oiwi Parker Jones
cs.CLcs.LGarXiv:2609.10296v12026
A Survey of Large Models in Sports
Yichen Xu, Jianzhe Ma, Chuhan Wang +4
cs.CLcs.CVarXiv:2608.14377v12026
Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment
Deepak Pandita, Christopher M. Homan
cs.CLarXiv:2608.30842v12026
Evaluating and Improving LLM Self-Modeling
Siqi Zeng, Andre N. Assis, Rowan Wang
cs.CLcs.AIarXiv:2608.30980v12026
ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding
Luxi Lin, Zhanpeng Zeng, Shuang Peng +2
cs.CLarXiv:2608.29748v12026
Do large language models scrutinise what they review? A multimodal audit of scoring calibration, error detection, and author-identity effects
Emad Alharbi
cs.CLcs.AIarXiv:2608.28626v12026
ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback
Min Zeng, Yuzhou Liu, Zhenyu Cao +5
cs.CLarXiv:2609.09072v12026
Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning
Tatul Danielyan, Mariam Avetisyan, Hrant Davtyan
cs.CLcs.IRarXiv:2608.29284v12026
More Capable, Less Faithful: A Multilingual Analysis of Mathematical (Un)Solvability Detection in LLMs
Maria-Eleni Zoumpoulidi, Nikolaos Xiros, Georgios Paraskevopoulos
cs.CLarXiv:2608.30463v12026
Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness
Pinzhen Chen, Koel Dutta Chowdhury, Xiaoya Xu +20
cs.CLcs.AIarXiv:2608.09766v12026
FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes
Prabhjot Singh, Somnath Luitel, Manmeet Singh +1
cs.CLcs.AIcs.LGarXiv:2608.26129v12026
Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence
Mohammadali Khodabandehlou, Bhaskar Krishnamachari
cs.CLcs.LGarXiv:2608.29934v12026
LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts
Daniela Occhipinti, Andrea Piergentili, Marco Guerini
cs.CLarXiv:2609.00222v12026
Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment
Mustafa Talha İlerisoy, Hung Manh Pham, Mathias Funk +2
cs.CLcs.AIcs.SDarXiv:2609.00055v12026

Computation and Language

A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation

EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion

Text Restoration of Ancient Documents with Language Models

OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding

When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models

PACE: Publisher-Adaptive Content Extraction via Agentic Automation

Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning

Editable Visual Design

Reliability Challenges in Diffusion Vision-Language Models

The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing

UIC-AIHealth4All at ArchEHR-QA 2026: Answer-First Evidence Grounding for Clinical Question Answering

Distinguishing Revision and Delayed Elaboration in Incremental Narrative Interpretation

AraMS-28k: The Largest Publicly Released Line-Level Dataset of Historical Arabic Manuscripts with Margin and Insertion-Anchor Annotations

Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry

Research Design Tracking and Assessment for the Social Sciences

Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking

Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation

Investigating Safety Vulnerabilities of Large Audio-Language Models Under Speaker Emotional Variations

How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation

MedUAG: Unified Understanding and Generation for Medical Multimodal Models

Reinforcement Learning for improving Large Language Models' Catalan text simplification capabilities

Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Registered Negative Result

A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models

Using Poly-Encoders for Computationally Efficient Automated Creativity Assessment

SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning

Are LLMs Safe Beyond Text: Do Emojis Expose Gaps in Safety Evaluation

DTOC: Dynamic Tool Output Compression for Adaptive Context Management in AI Agents

Provenance Before Prose: Claim-Locked Reporting

LLM-Derived Preference Judgments Are Not Self-Consistent

Less can be More: Relieving RAG Bottlenecks via Evidence Frontloading and Pressure-Adaptive Budgeting

Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs

EgoArgus: Benchmarking VLMs as Situational Assistants for Modality-Grounded User Supports

STAGEET: Stage-wise Typed Edit Tagging for Grammatical Error Correction with Arabic as a Case Study

The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence

Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprinting

Evaluating AI Generated Summaries for Cancer Patients

Dr. Claw: An AI Scientist Workspace for Vibe Research

Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models

GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments

Personalized Auto-Research: Towards a True AI Co-Scientist

Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts

Slow to See, Slow to Suppress: Understanding the Effects of Modality in Context-Memory Conflicts

Prompting is not enough: supervised baselines and leakage control for measuring shared decision-making with LLMs in pediatric encounters

How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution

The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure

The Hallucination Snowball: Modeling Error Propagation as State Transitions in Multi-Agent LLM Pipelines

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

A Survey of Large Models in Sports

Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment

Evaluating and Improving LLM Self-Modeling

ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding

Do large language models scrutinise what they review? A multimodal audit of scoring calibration, error detection, and author-identity effects

ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback

Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning

More Capable, Less Faithful: A Multilingual Analysis of Mathematical (Un)Solvability Detection in LLMs

Cultivar: A Contrastive and Locale-Oriented Translation Benchmark for Investigating Contamination and Localisation Robustness

FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes

Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence

LLM-as-a-Demographic: Whom Sociodemographic Prompting Helps, and Whom It Hurts

Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment