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)

7,981 to 8,040 of 11,332

When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory
Kazuki Nakayashiki
cs.IRcs.AIcs.CLarXiv:2608.25553v12026
Controllable Affective Generation via Latent Vector Steering
Xixian Yong, Siyuan Chang, Yingying Zhang +2
cs.CLcs.AIarXiv:2608.25569v12026
A Storage-Retrieval Gap in Parametric Knowledge Graph Memory
Martino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov +1
cs.LGcs.CLcs.IRarXiv:2608.25489v12026
TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving
Hongqiu Ni, Han Tian, Chi Zhang +2
cs.CLarXiv:2608.25523v12026
From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection
Zhibo Hou, Fan Zhao, Zhiyu An +1
cs.CLcs.LGarXiv:2608.25243v12026
Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips
Huakang Lin, Tiancheng Zheng, Mingxuan Sun +4
cs.CLarXiv:2608.25276v12026
Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation
Pratyay Banerjee, Ankit Chadha
cs.CLcs.AIarXiv:2608.25277v12026
CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval
Zhiyuan Li, Linyuan Gao, Xuechun Ding +3
cs.AIcs.CLarXiv:2608.25500v12026
Large-Scale Adversarial Training for Vision-and-Language Representation Learning
Zhe Gan, Yen-Chun Chen, Linjie Li +3
cs.CVcs.CLcs.LGarXiv:2006.06195v22020
Virgil: Navigating Explainability for Transformer-based Language Models
Martino Ciaperoni, Sezer Kutluk, Benedetta Muscato +2
cs.CLcs.LGarXiv:2608.25555v12026
GUIDE: Generative Unsupervised Chinese Query Correction via Phonetic and Visual Shared-ID Encoding
Lei Yang, Binbin Huang, Jiwei Tan +4
cs.CLarXiv:2608.25343v12026
ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning Chains
Jinpu Jiang, Xuan Wu, Wenhao Song +6
cs.CLcs.IRarXiv:2608.25487v12026
Learning Factorized Multimodal Representations
Yao-Hung Hubert Tsai, Paul Pu Liang, Amir Zadeh +2
cs.LGcs.CLcs.CVarXiv:1806.06176v32018
The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion
Chenglong Ma, Xinye Wanyan, Danula Hettiachchi +2
cs.IRcs.CLarXiv:2608.25245v12026
From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation
Lukas Edman, Daryna Dementieva, Alexander Fraser
cs.CLarXiv:2608.25605v12026
Text Summarization Techniques: A Brief Survey
Mehdi Allahyari, Seyedamin Pouriyeh, Mehdi Assefi +4
cs.CLarXiv:1707.02268v32017
Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study
Thibault Bañeras-Roux, Shashi Kumar, Driss Khalil +6
cs.CLarXiv:2608.25574v12026
Natural Language Input, Semantic Track Representation, and LLM Inference: Making the Maritime Information Exchange Model Tractable
Frederick Roth
cs.AIcs.CLarXiv:2608.24892v12026
Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens
Shi-Qi Yan, Kai-Xuan Ding, Chao-Hong Tan +4
cs.CLarXiv:2608.25347v12026
A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation
Bing Shao, Jiazheng Zhang, Long Ma +9
cs.LGcs.CLarXiv:2608.25643v12026
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
Xingyu Chen, Jiahao Xu, Tian Liang +11
cs.CLarXiv:2412.21187v22024
PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consulting
Evgenii Garmashov, Nikita Kulin, Artur Khairullin +5
cs.HCcs.AIcs.CLarXiv:2608.24907v12026
CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities
Mina Lee, Percy Liang, Qian Yang
cs.HCcs.CLarXiv:2201.06796v22022
CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT
Akshay Smit, Saahil Jain, Pranav Rajpurkar +3
cs.CLcs.IRcs.LGarXiv:2004.09167v32020
AWM: Answerable Working Memory for Long-Document VQA Agents
Dongzhuoran Zhou, Yuqicheng Zhu, Yule Liu +5
cs.CLarXiv:2608.25618v12026
Offline bilingual word vectors, orthogonal transformations and the inverted softmax
Samuel L. Smith, David H. P. Turban, Steven Hamblin +1
cs.CLcs.AIcs.IRarXiv:1702.03859v12017
Recommender Systems in the Era of Large Language Models (LLMs)
Zihuai Zhao, Wenqi Fan, Jiatong Li +8
cs.IRcs.AIcs.CLarXiv:2307.02046v62023
Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection
Pardis Ranjbar-Noiey, Natalie Parde
cs.CLcs.LGarXiv:2608.25028v12026
A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques
Mehdi Allahyari, Seyedamin Pouriyeh, Mehdi Assefi +4
cs.CLcs.AIcs.IRarXiv:1707.02919v22017
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
Taylor Shin, Yasaman Razeghi, Robert L. Logan +2
cs.CLcs.LGarXiv:2010.15980v22020
MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation
Pia Chouayfati, Alexander M. Fichtl, Miriam Anschütz +2
cs.CLarXiv:2608.25085v12026
HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench
Matthew Flathers, Phuong Anh Nguyen, Jill Noorily +7
cs.CLcs.AIcs.CYarXiv:2608.25071v12026
Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy
Zhihong Shao, Yeyun Gong, Yelong Shen +3
cs.CLarXiv:2305.15294v22023
DataKernelBench: Can LLMs Optimize Database Queries on GPUs?
Gokul Karthik Kumar, Yotam Perlitz, Corey Lammie +2
cs.CLcs.AIcs.DBarXiv:2608.25061v12026
Padamitra: Grounded Glossary Generation for Classical Sanskrit
Manoj Balaji Jagadeeshan, Sai Pragnaan Marala, Pawan Goyal
cs.CLarXiv:2608.25038v12026
A Primer on Computational Semantics for Artificial Intelligence Systems
Casey Kennington
cs.CLcs.AIarXiv:2608.25022v12026
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training
Linjie Li, Yen-Chun Chen, Yu Cheng +3
cs.CVcs.CLcs.LGarXiv:2005.00200v22020
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
Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
Philipp E. Glass, Allan Tucker, Yongmin Li +1
cs.CLcs.AIcs.LGarXiv:2608.24988v12026
Dissecting Recall of Factual Associations in Auto-Regressive Language Models
Mor Geva, Jasmijn Bastings, Katja Filippova +1
cs.CLarXiv:2304.14767v32023
Unsupervised Post-Training of Foundation Models: A Survey
Yijie Xu, Qianyi Cai, Huizai Yao +9
cs.CLcs.AIcs.CVarXiv:2608.24982v12026
Colorless green recurrent networks dream hierarchically
Kristina Gulordava, Piotr Bojanowski, Edouard Grave +2
cs.CLarXiv:1803.11138v12018
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Chrisantha Fernando, Dylan Banarse, Henryk Michalewski +2
cs.CLcs.AIcs.LGarXiv:2309.16797v12023
Generative Gap Filling
Yonathan A. Arbel, David A. Hoffman
cs.CYcs.CLarXiv:2608.21401v12026
LESS: Selecting Influential Data for Targeted Instruction Tuning
Mengzhou Xia, Sadhika Malladi, Suchin Gururangan +2
cs.CLcs.AIcs.LGarXiv:2402.04333v32024
MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers +4
cs.CLarXiv:2102.01454v32021
Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities
Hai Pham, Paul Pu Liang, Thomas Manzini +2
cs.LGcs.CLcs.CVarXiv:1812.07809v22018
NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
Chankyu Lee, Rajarshi Roy, Mengyao Xu +4
cs.CLcs.AIcs.IRarXiv:2405.17428v32024
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
Alexander Ku, Peter Anderson, Roma Patel +2
cs.CVcs.AIcs.CLarXiv:2010.07954v12020
Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment
Jiangang Hao
cs.CLcs.AIcs.HCarXiv:2608.24920v12026
Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores
Haoran Jisun
cs.CLcs.HCcs.LGarXiv:2608.24901v12026
Multilingual E5 Text Embeddings: A Technical Report
Liang Wang, Nan Yang, Xiaolong Huang +3
cs.CLcs.IRarXiv:2402.05672v12024
Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards?
Lorenzo Molfetta, Alessio Cocchieri, Luca Ragazzi +3
cs.CYcs.AIcs.CLarXiv:2608.21409v12026
The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generation
Ashritha Gonuguntla
cs.CVcs.CLcs.LGarXiv:2608.21713v12026
Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing
Israt Moyeen Noumi, Tarannum Ahmed Nowshin, Md. Mehedi Hasan Nipu +3
cs.CLcs.AIcs.CRarXiv:2608.21423v12026
Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding
Yisong Xiao, Aishan Liu, Yongxin Huang +6
cs.CLcs.AIarXiv:2608.21415v12026
Evidence-State Reliability Under Controlled Degradation: Parser-Validity Divergence in a Multi-Stage LLM Pipeline
Naimur Rahman
cs.CLarXiv:2608.21559v12026
TANGO: Token-Aggregated Nonlinear Gating Operators for Natural and Formal Language Modeling
Joshua Nunley
cs.LGcs.CLarXiv:2608.22117v12026
LLMs for Survey Text Analysis - A Performance Comparison Between Humans and GPT-5 on Inductive Content Analysis
Leonardo Bergmann, Renata Gheorghiu, Ana Gvritishvili +3
cs.AIcs.CLcs.HCarXiv:2608.22417v12026
Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification
Jérémie Dentan, Alexi Canesse, Mahammed El Sharkawy +1
cs.CLarXiv:2608.22506v12026

Computation and Language

When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory

Controllable Affective Generation via Latent Vector Steering

A Storage-Retrieval Gap in Parametric Knowledge Graph Memory

TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving

From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection

Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips

Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation

CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

Virgil: Navigating Explainability for Transformer-based Language Models

GUIDE: Generative Unsupervised Chinese Query Correction via Phonetic and Visual Shared-ID Encoding

ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning Chains

Learning Factorized Multimodal Representations

The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion

From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content Mitigation

Text Summarization Techniques: A Brief Survey

Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative Study

Natural Language Input, Semantic Track Representation, and LLM Inference: Making the Maritime Information Exchange Model Tractable

Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens

A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

PA-CoT: Profile-Adaptive Chain-of-Thought for Personalized Nutritional Consulting

CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities

CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT

AWM: Answerable Working Memory for Long-Document VQA Agents

Offline bilingual word vectors, orthogonal transformations and the inverted softmax

Recommender Systems in the Era of Large Language Models (LLMs)

Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection

A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques

AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

MTDiag: A Multi-Turn Diagnostic Dataset Towards Clinically Meaningful LLM Evaluation

HealthBench-Psych: A Mental Health Subset of OpenAI's HealthBench

Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy

DataKernelBench: Can LLMs Optimize Database Queries on GPUs?

Padamitra: Grounded Glossary Generation for Classical Sanskrit

A Primer on Computational Semantics for Artificial Intelligence Systems

HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training

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

Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal

Dissecting Recall of Factual Associations in Auto-Regressive Language Models

Unsupervised Post-Training of Foundation Models: A Survey

Colorless green recurrent networks dream hierarchically

Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

Generative Gap Filling

LESS: Selecting Influential Data for Targeted Instruction Tuning

MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers

Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities

NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding

Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment

Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores

Multilingual E5 Text Embeddings: A Technical Report

Sycophants in the Courtroom: Are LLMs Fragile to Juridical Authority and Evolving Legal Standards?

The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generation

Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing

Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding

Evidence-State Reliability Under Controlled Degradation: Parser-Validity Divergence in a Multi-Stage LLM Pipeline

TANGO: Token-Aggregated Nonlinear Gating Operators for Natural and Formal Language Modeling

LLMs for Survey Text Analysis - A Performance Comparison Between Humans and GPT-5 on Inductive Content Analysis

Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty Quantification