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)

241 to 300 of 11,233

Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
Mor Geva, Avi Caciularu, Kevin Ro Wang +1
cs.CLarXiv:2203.14680v32022
Compositional Multilingual and Behavioral Attribute Steering
Hyun Gu Kang, Daniil Gurgurov, Tanja Baeumel +2
cs.CLarXiv:2609.08410v12026
Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
Harsh Kohli, Srinivasan Parthasarathy, Huan Sun +1
cs.CLcs.AIcs.LGarXiv:2604.07822v22026
PLDR-LLMs Reason At Self-Organized Criticality
Burc Gokden
cs.AIcs.CLcs.LGarXiv:2603.23539v12026
SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?
Azmine Toushik Wasi, Wahid Faisal, Abdur Rahman +12
cs.CVcs.CEcs.CLarXiv:2602.03916v32026
CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning
Eric Onyame, Akash Ghosh, Subhadip Baidya +3
cs.AIcs.CLarXiv:2601.13262v22026
Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior
Rafal Kocielnik, Pengrui Han, Peiyang Song +5
cs.AIcs.CLcs.CYarXiv:2606.12730v12026
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
Zhangyi Hu, Chenhui Liu, Tian Huang +6
cs.LGcs.AIcs.CLarXiv:2605.23491v22026
Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data
Spencer Whitehead, Jacob Phillips, Sean Hendryx
cs.CLcs.CVarXiv:2409.00238v12024
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
Wei Liu, Ruochen Zhou, Yiyun Deng +5
cs.CLcs.AIcs.LGarXiv:2505.15612v12025
Emergent Abilities in Large Language Models: A Survey
Leonardo Berti, Flavio Giorgi, Gjergji Kasneci
cs.LGcs.AIcs.CLarXiv:2503.05788v32025
Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models
Yuzhe Shang, Pengzhi Gao, Wei Liu +2
cs.CLarXiv:2602.11961v32026
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
Mantas Mazeika, Xuwang Yin, Rishub Tamirisa +8
cs.LGcs.AIcs.CLarXiv:2502.08640v22025
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Zefan Cai, Yichi Zhang, Bofei Gao +8
cs.CLcs.AIarXiv:2406.02069v42024
Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
Eugene Kharitonov, Morgane Rivière, Gabriel Synnaeve +4
eess.AScs.CLcs.SDarXiv:2007.00991v12020
MiniLLM: On-Policy Distillation of Large Language Models
Yuxian Gu, Li Dong, Furu Wei +1
cs.CLcs.AIarXiv:2306.08543v62023
Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic
cs.CRcs.CLcs.SEarXiv:2605.29737v12026
Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment
Saketh Reddy Vemula, Sandipan Dandapat, Dipti Misra Sharma +1
cs.CLcs.AIarXiv:2508.08424v32025
R-PRM: Reasoning-Driven Process Reward Modeling
Shuaijie She, Junxiao Liu, Yifeng Liu +3
cs.CLarXiv:2503.21295v12025
Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions
Alicia Parrish, Harsh Trivedi, Ethan Perez +4
cs.CLarXiv:2204.05212v22022
Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes
Izzy Chaiken, Aditya Khowal, Neha A. Sathe +2
cs.CLcs.LGphysics.soc-pharXiv:2609.17532v12026
Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits
Victoria Popa, Guglielmo Cola, Caterina Senette +1
cs.CLarXiv:2609.17534v12026
Understanding AI Provider Recommendations in Local Service Markets
Hazem Ibrahim, Yasir Zaki
cs.CYcs.CLcs.IRarXiv:2609.18341v12026
DANTINOX: A Unified Framework for Multi-Paradigm Language Modeling
Marco Simoni, Aleksandar Fontana, Giulio Rossolini +1
cs.CLarXiv:2609.17535v12026
Relation Before Entity: Deferred Commitment in Language Model Factual Recall
Divyansh Agarwal
cs.CLarXiv:2609.17537v12026
Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents
Jiyue Jiang, Ziyi Li, He Hu +9
cs.CLarXiv:2609.17536v12026
Register Bias in Complexity-Based Large Language Model Routing
Simran Koul
cs.CLcs.CYarXiv:2609.17542v12026
From Pixels to Pairs: A Comprehensive Benchmark of LLM-Based Key-Value Extraction in Noisy Document Settings
Zahra Anvari, Vassilis Athitsos
cs.CLcs.CVarXiv:2609.17538v12026
Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues
Arefeh Kazemi, Hamza Qadeer, Sinan Asci +2
cs.CLcs.CYarXiv:2609.17549v12026
Cognitive Bias in Decision-Making with LLMs
Jessica Echterhoff, Yao Liu, Abeer Alessa +2
cs.AIcs.CLarXiv:2403.00811v32024
How AI Assistants Respond to Repeated Abuse
William Guey, Wei Zhang, Pierrick Bougault +4
cs.CLarXiv:2609.17547v12026
Myovox: Reading Speech from the Muscles of the Face
Varshith Madishetty
cs.CLarXiv:2609.17548v12026
Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation
Jiacheng Xie, Xiaoting Tang, Yang Yu +9
cs.CLcs.CYarXiv:2609.17544v12026
The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models
Elzbieta Dawidek
cs.CLarXiv:2609.17553v12026
Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks
Arth Singh
cs.CLarXiv:2609.17552v12026
No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback
Saad Aamir, Muhammad Awais Bin Adil
cs.CLcs.LGarXiv:2609.17550v12026
English Word Sense Disambiguation in 2026: When the Labels Become the Bottleneck
Vassili Philippov, Amro Salman, Dmitrii Andreev +4
cs.CLarXiv:2609.17554v12026
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
Amir Ziashahabi, Hossein Entezari Zarch, Lei Gao +2
cs.LGcs.CLcs.DCarXiv:2609.17943v12026
Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant
Maksym Taranukhin, Vered Shwartz
cs.CLarXiv:2609.17546v12026
AutoNeural: Co-Designing Vision-Language Models for NPU Inference
Wei Chen, Liangmin Wu, Yunhai Hu +9
cs.CLarXiv:2512.02924v32025
Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation
Ting-Wei Chang, Hen-Hsen Huang, Hsin-Hsi Chen
cs.CLarXiv:2609.17398v12026
The Geometry of Reasoning: Flowing Logics in Representation Space
Yufa Zhou, Yixiao Wang, Xunjian Yin +2
cs.AIcs.CLcs.LGarXiv:2510.09782v22025
Where Should a Document Live: Context, Representations, or Parameters?
Nathanaël Carraz Rakotonirina, Momchil Hardalov, Gonzalo Iglesias +1
cs.CLcs.AIarXiv:2609.17346v12026
Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement
Ting-Wei Chang, Po-Chun Chen, Hen-Hsen Huang +1
cs.CLarXiv:2609.16800v12026
MudawanSn: A Gold-Standard Wolof-Arabic Parallel Corpus for Machine Translation
Mouhamed Mbaye, Thierno Diop
cs.CLarXiv:2609.17539v12026
GenRec: Large Language Model for Generative Recommendation
Jianchao Ji, Zelong Li, Shuyuan Xu +4
cs.IRcs.AIcs.CLarXiv:2307.00457v22023
A Comprehensive Review of Generative Physical Artificial Intelligence
Satyam Gaba, Krutiksinh Rana, Siva Sai +2
cs.ROcs.AIcs.CLarXiv:2609.18111v12026
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
Xueyu Hu, Ziyu Zhao, Shuang Wei +14
cs.CLcs.AIarXiv:2401.05507v32024
The Functionalizer: Lossless Functional Decomposition for Subword Tokenization
Connor Makowski, Willem Guter
cs.CLarXiv:2609.15991v12026
A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education
Jacob Doughty, Zipiao Wan, Anishka Bompelli +12
cs.CYcs.AIcs.CLarXiv:2312.03173v12023
Agent as Policy for Robotic Manipulation
Mengzhao Jia, Yang Lin, Xixin Zhang +3
cs.CLarXiv:2609.12541v22026
Optimal Model Activation Policies for Inference Networks of Large Language Models
Foivos Charalampakos, Md Ibrahim Ibne Alam, Iordanis Koutsopoulos +1
cs.CLarXiv:2609.15992v12026
TAME: Token Attribution and Masking for Emergent misalignment
Md Rayhanul Masud, Md Rizwan Parvez
cs.LGcs.AIcs.CLarXiv:2609.16754v12026
Single Document Extractive Summarization using Domination in Hypergraph
Aamir Miyajiwala, Aabha Pingle, Sheetal Sonawane +1
cs.CLcs.LGarXiv:2609.15993v12026
Self-reported archetypes and behavioral failures in Large Language Models
Tabia Tanzin Prama, Calla Glavin Beauregard, Christopher M. Danforth +1
cs.CLphysics.soc-pharXiv:2609.15998v12026
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
Akide Liu, Jing Liu, Zizheng Pan +3
cs.CLcs.AIcs.LGarXiv:2405.14366v22024
Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety
Abu Saif Md Nasim Uddin, Mohamed Abdel-Aty, Zubayer Islam +2
cs.CLcs.LGarXiv:2609.15997v12026
BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
Yifei Wang, Dizhan Xue, Shengjie Zhang +1
cs.CLcs.AIcs.CRarXiv:2406.03007v12024
Comment on arXiv:2607.01233: Survivorship Bias in Published-Paper Baselines for Research-Idea Distributions
Fredrik A. Dahl
cs.CLarXiv:2609.15996v12026
Bias Audits Detect Bias but Disagree on Ranking: Evidence from Ten Instruments and Ten Frontier Models
William Guey, Pierrick Bougault, Wei Zhang +2
cs.CLarXiv:2609.15995v12026

Computation and Language

Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space

Compositional Multilingual and Behavioral Attribute Steering

Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers

PLDR-LLMs Reason At Self-Organized Criticality

SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test

Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

Emergent Abilities in Large Language Models: A Survey

Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Data Augmenting Contrastive Learning of Speech Representations in the Time Domain

MiniLLM: On-Policy Distillation of Large Language Models

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

Rethinking Tokenization for Rich Morphology: The Dominance of Unigram over BPE and Morphological Alignment

R-PRM: Reasoning-Driven Process Reward Modeling

Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions

Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes

Faking Good and Faking Bad in LLMs: Response Distortion Across Dark Triad Personality Traits

Understanding AI Provider Recommendations in Local Service Markets

DANTINOX: A Unified Framework for Multi-Paradigm Language Modeling

Relation Before Entity: Deferred Commitment in Language Model Factual Recall

Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents

Register Bias in Complexity-Based Large Language Model Routing

From Pixels to Pairs: A Comprehensive Benchmark of LLM-Based Key-Value Extraction in Noisy Document Settings

Do Social Patterns Hold in Synthetic Data? Analyzing Cyberbullying Dynamics in LLM-Generated and Authentic Dialogues

Cognitive Bias in Decision-Making with LLMs

How AI Assistants Respond to Repeated Abuse

Myovox: Reading Speech from the Muscles of the Face

Large Language Models Versus Physicians in Traditional Chinese Medicine: A Real-World Clinical Case Evaluation

The Limits of BPE Tokenization in Polish: Segmentation-Flexional Forms, Grammatical Anchoring, and First-Person Stability in Inflectional Language Models

Does Moral Reasoning Training Help or Hurt? Red-Teaming RL-Trained Ethical Agents with Persona Attacks

No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback

English Word Sense Disambiguation in 2026: When the Labels Become the Bottleneck

ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference

Legal LLM Hallucination Should Be Evaluated as Failure of Legal Warrant

AutoNeural: Co-Designing Vision-Language Models for NPU Inference

Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation

The Geometry of Reasoning: Flowing Logics in Representation Space

Where Should a Document Live: Context, Representations, or Parameters?

Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement

MudawanSn: A Gold-Standard Wolof-Arabic Parallel Corpus for Machine Translation

GenRec: Large Language Model for Generative Recommendation

A Comprehensive Review of Generative Physical Artificial Intelligence

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

The Functionalizer: Lossless Functional Decomposition for Subword Tokenization

A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education

Agent as Policy for Robotic Manipulation

Optimal Model Activation Policies for Inference Networks of Large Language Models

TAME: Token Attribution and Masking for Emergent misalignment

Single Document Extractive Summarization using Domination in Hypergraph

Self-reported archetypes and behavioral failures in Large Language Models

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Crash Narrative-Guided Countermeasure Recommendation Using Large Language Models: A Retrieval-Augmented Generation Framework for Intersection Safety

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

Comment on arXiv:2607.01233: Survivorship Bias in Published-Paper Baselines for Research-Idea Distributions

Bias Audits Detect Bias but Disagree on Ranking: Evidence from Ten Instruments and Ten Frontier Models