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)

10,621 to 10,680 of 11,252

Distributed Representations of Words and Phrases and their Compositionality
Tomas Mikolov, Ilya Sutskever, Kai Chen +2
cs.CLcs.LGstat.MLarXiv:1310.4546v12013
Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See
Ayoub Kirouane, Christos Petrocheilos
cs.CLcs.LGcs.ROarXiv:2608.17744v12026
HarmProfile: Characterizing Harmful Distributions in Frontier LLMs
Zhouyuan Ma, Yutao Wu, Hanxun Huang +6
cs.CLcs.AIarXiv:2608.14577v12026
Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents
Wei-Chieh Huang, Weizhi Zhang, Yuchen Wu +12
cs.CLarXiv:2608.15008v12026
Building Social World Models with Large Language Models
Haofei Yu, Yining Zhao, Guanyu Lin +1
cs.SIcs.CLarXiv:2606.11482v12026
Beyond Single Object: Learning 3D Relations with Large Language Models
Kohsuke Ide, Ryousuke Yamada, Yue Qiu +4
cs.CVcs.AIcs.CLarXiv:2608.15710v12026
Do Language Models Consistently Encode the Current Year?
Suze van Adrichem, Aditi Bhaskar, Diyi Yang +2
cs.CLcs.LGarXiv:2608.15507v12026
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
Víctor Yeste, Paolo Rosso
cs.CLcs.AIcs.LGarXiv:2605.22641v32026
Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles
Roman Neruda, Martin Bakoš, Josef Šlerka +3
cs.CYcs.CLcs.LGarXiv:2608.15871v12026
Polaris: Learning to Generate Table Descriptions from Retrieval Feedback
Ting Cai, Tuan Minh Phan, AnHai Doan
cs.CLcs.DBarXiv:2608.17171v12026
Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning
Yanxi Chen, Weijie Shi, Yuexiang Xie +4
cs.LGcs.AIcs.CLarXiv:2606.20002v12026
The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarks
Luis M. Sanchez, Kosrow Dehnad
cs.IRcs.CLarXiv:2608.16096v12026
Architecture-Dependent Causal Transfer of Activation States Across Large Language Models
Fernando Cardenas Piepereit
cs.CLcs.LGarXiv:2608.16347v12026
Margin-Regularized Structured Semantic Alignment for Brain-Language Correspondence
Jiaqi Wang, Huawen Hu, Shu Zhang
cs.CLcs.LGarXiv:2608.16975v12026
Does the LM Head Create a Harmful Gradient Bottleneck? A Causal Test
Anand Murugan
cs.CLarXiv:2608.16671v12026
Executable Code Knowledge: Code as a Native, Validation-Carrying Knowledge Representation for AI Coding Agents
Xueping Gao
cs.CLarXiv:2608.16295v12026
Preference Is Not Intervention: The Structure and Stability Boundaries of Reader-Specific Evidence Utility
Shi Zhou
cs.CLarXiv:2608.17781v12026
Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text
Benjamin Belay
cs.CLcs.AIarXiv:2608.16868v12026
CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion
Zheling Tan, Jin Gao, Dequan Wang
cs.CLarXiv:2608.17911v12026
Grading Needs a Rubric, Not Intelligence
Jhen-Ke Lin
cs.CLcs.AIarXiv:2608.17938v12026
What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations
Xiaonan Xu, Wenjing Wu
cs.SEcs.AIcs.CLarXiv:2608.17719v12026
CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method
Jin Su, Zhuofeng Zhao, Huanhuan Wang +1
cs.CLcs.AIarXiv:2608.17536v12026
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Jundong Xu, Qingchuan Li, Jiaying Wu +11
cs.CLarXiv:2606.13681v22026
Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation
Zhongzhu Zhou, Qingyang Wu, Junxiong Wang +4
cs.LGcs.CLarXiv:2606.16429v12026
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks
Jingru Guo, Xiangyuan Xue, Lian Zhang +6
cs.CLarXiv:2606.15872v12026
AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization
Junlong Tong, Wenqi Xu, Yingqi Fan +4
cs.CLarXiv:2606.14694v22026
PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions
Chenxin Li, Zhengyao Fang, Zhengyang Tang +18
cs.CLarXiv:2606.14832v12026
Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus
Yuheng Lu, Qingcheng Zeng, Heli Qi +6
cs.CLcs.IRarXiv:2606.15345v22026
Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs
Nafiseh Nikeghbal, Amir Hossein Kargaran, Shaghayegh Kolli +1
cs.CLarXiv:2606.16011v12026
Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations
Guy Rotman, Adi Kopilov, Danit Berger Zalmanson +1
cs.CLarXiv:2606.15641v12026
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks
Hongcheng Gao, Hailong Qu, Jingyi Tang +18
cs.AIcs.CLarXiv:2606.09669v22026
Attacks on Machine-Text Detectors Retain Stylistic Fingerprints
Rafael Rivera Soto, Barry Chen, Nicholas Andrews
cs.CLcs.AIcs.LGarXiv:2505.14608v32025
Inference-Time Mitigation of Adversarial Political Bias in Large Language Models
Tejaswi V. Panchagnula, Bruce Coburn, Bryce J. Dietrich +3
cs.CLcs.AIarXiv:2608.14629v12026
SeqFeed: Improving Agentic RTL Code Generation with Sequential Behavior Feedback
Yuxin Du, Juxin Niu, Tao Hu +3
cs.ARcs.CLarXiv:2608.16934v12026
pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier
Gautam Kishore
cs.LGcs.AIcs.CLarXiv:2608.14658v12026
DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance
Zihan Li, Feifei Li, Wenhui Que
cs.LGcs.CLarXiv:2608.14644v12026
Characterizing Rhetorical Misalignment in Decision-Making with Language Models
Zirui Cheng, Joey Chan, Simo Du +3
cs.CLcs.AIarXiv:2608.14630v12026
Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays
Bhaskar Gurram
cs.LGcs.AIcs.CLarXiv:2608.14639v12026
Efficient RLVR Scheduling via Graph-Structured Online Difficulty Estimation
Zhizhao Liu, Zhiliang Tian, Xi Wang +4
cs.LGcs.AIcs.CLarXiv:2608.17941v12026
Where Does Retrieval Fail? Evaluating RAG Architectures for Agricultural Advisory
Khan Raiyan Ibne Reza, Sanjana Aktar Maria, Sumaiya Tabassum Nimi
cs.CLarXiv:2608.14886v12026
Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints
Bruno Chicelli, Henrique Alves, Rodrigo Anselmo +3
cs.CLcs.AIcs.CVarXiv:2608.15032v12026
Beyond the pale: Assessing prevalence and contents of extremist speech in LLM training data
Dmitry Nikolaev, Ashley A. Mattheis
cs.CLarXiv:2608.14813v12026
Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews
Gilberto Sussumu Hida, Danilo Monteiro Ribeiro, Clayton Suguio Hida
cs.CLcs.AIarXiv:2608.14737v12026
Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks
Volodymyr Ovcharov
cs.CLcs.AIcs.CYarXiv:2608.15428v12026
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
Chao Chen, Chengzu Li, Zhiwei Li +2
cs.CLarXiv:2606.17682v12026
LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI
Lalit Yadav, Akshaj Gurugubelli
cs.AIcs.CLcs.LGarXiv:2606.18021v12026
Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States
Denis Peskoff, Joe Barrow, Christopher Vu +1
cs.CLcs.CYcs.LGarXiv:2606.19334v12026
Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
Xiaoyue Xu, Sikui Zhang, Xiaorong Wang +2
cs.CLcs.AIarXiv:2606.18831v12026
StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs
Shaghayegh Kolli, Timo Cavelius, Nafiseh Nikeghbal +2
cs.CLcs.CVarXiv:2606.20527v12026
Variable-Width Transformers
Zhaofeng Wu, Oliver Sieberling, Shawn Tan +3
cs.CLarXiv:2606.18246v12026
MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval
Amirhossein Abaskohi, Raymond Li, Gaetano Cimino +3
cs.CLcs.IRarXiv:2606.18508v12026
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG
Amirhossein Abaskohi, Issam H. Laradji, Peter West +1
cs.CLcs.IRarXiv:2606.18381v12026
Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish
Tolga Şakar
cs.CLcs.AIarXiv:2606.18717v12026
Sumi: Open Uniform Diffusion Language Model from Scratch
Mengyu Ye, Keito Kudo, Wataru Ikeda +3
cs.CLcs.LGarXiv:2606.19005v12026
PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models
Yueyi Sun, Yuhao Wang, Jason Li +8
cs.CVcs.AIcs.CLarXiv:2606.19534v12026
HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization
Zhentao Tan, Wei Chen, Jingyi Shen +4
cs.CLarXiv:2606.20097v12026
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
Jincheng Zhong, Weizhi Wang, Che Jiang +5
cs.CLcs.SEarXiv:2606.23654v12026
PhoneBuddy: Training Open Models for Agentic Phone Use
Zhengyang Tang, Xin Lai, Pengyuan Lyu +23
cs.CLcs.AIarXiv:2606.23049v22026
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
Haoling Li, Kai Zheng, Jie Wu +4
cs.AIcs.CLcs.CVarXiv:2606.23543v12026
OpenBioRQ: Unsolved Biomedical Research Questions for Agents
Minbyul Jeong
cs.CLarXiv:2606.21959v12026

Computation and Language

Distributed Representations of Words and Phrases and their Compositionality

Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

Building Social World Models with Large Language Models

Beyond Single Object: Learning 3D Relations with Large Language Models

Do Language Models Consistently Encode the Current Year?

More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts

Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles

Polaris: Learning to Generate Table Descriptions from Retrieval Feedback

Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning

The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarks

Architecture-Dependent Causal Transfer of Activation States Across Large Language Models

Margin-Regularized Structured Semantic Alignment for Brain-Language Correspondence

Does the LM Head Create a Harmful Gradient Bottleneck? A Causal Test

Executable Code Knowledge: Code as a Native, Validation-Carrying Knowledge Representation for AI Coding Agents

Preference Is Not Intervention: The Structure and Stability Boundaries of Reader-Specific Evidence Utility

Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text

CABLE: Extending the Reach of Memory Retrieval via Complementary Antecedent-Based Linking and Expansion

Grading Needs a Rubric, Not Intelligence

What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations

CoAL-RAG: A Complexity-Aware Legal Retrieval-Augmented Generation Method

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation

SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks

AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization

PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions

Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus

Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs

Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations

SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks

Attacks on Machine-Text Detectors Retain Stylistic Fingerprints

Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

SeqFeed: Improving Agentic RTL Code Generation with Sequential Behavior Feedback

pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier

DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance

Characterizing Rhetorical Misalignment in Decision-Making with Language Models

Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays

Efficient RLVR Scheduling via Graph-Structured Online Difficulty Estimation

Where Does Retrieval Fail? Evaluating RAG Architectures for Agricultural Advisory

Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints

Beyond the pale: Assessing prevalence and contents of extremist speech in LLM training data

Class Imbalance and Batch Effects in LLM-Based Screening for Systematic Reviews

Gated Against One Model, Open to the Next: Option-Only Solvability in Legal Multiple-Choice Benchmarks

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI

Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs

Variable-Width Transformers

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish

Sumi: Open Uniform Diffusion Language Model from Scratch

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions

PhoneBuddy: Training Open Models for Agentic Phone Use

VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct

OpenBioRQ: Unsolved Biomedical Research Questions for Agents