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)

15,121 to 15,180 of 18,979

KinyaEmbed: Contrastive Sentence Embeddings for Kinyarwanda via Multi-Stage Curriculum Training
Ireddi Rakshitha, Devavarapu Yashwanth, Ntakirutimana Pierre
cs.CLarXiv:2608.26941v12026
SWE-RM: Execution-free Feedback For Software Engineering Agents
KaShun Shum, Binyuan Hui, Jiawei Chen +6
cs.CLarXiv:2512.21919v12025
Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions
John Joon Young Chung, Ece Kamar, Saleema Amershi
cs.CLarXiv:2306.04140v12023
Large Language Models can Strategically Deceive their Users when Put Under Pressure
Jérémy Scheurer, Mikita Balesni, Marius Hobbhahn
cs.CLcs.AIcs.LGarXiv:2311.07590v42023
Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference
Shuqing Shi, Ziyan Wang, Milind Tambe +1
cs.CLarXiv:2610.07587v12026
#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
Keming Lu, Hongyi Yuan, Zheng Yuan +5
cs.CLcs.AIcs.LGarXiv:2308.07074v22023
Understanding Undesirable Word Embedding Associations
Kawin Ethayarajh, David Duvenaud, Graeme Hirst
cs.CLarXiv:1908.06361v22019
Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech
Margherita Fanton, Helena Bonaldi, Serra Sinem Tekiroglu +1
cs.CLcs.CYarXiv:2107.08720v12021
DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text
Mohamed Mady, Yupei Li, Johannes Reschke +1
cs.CLcs.CRarXiv:2610.00883v12026
Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning
Seungmin Oh, Donggeon Lee, Jongbin Ryu
cs.CLcs.AIarXiv:2609.06974v12026
DarkBench: Benchmarking Dark Patterns in Large Language Models
Esben Kran, Hieu Minh "Jord" Nguyen, Akash Kundu +3
cs.CLcs.AIcs.CYarXiv:2503.10728v12025
Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity
Leon Engländer, Sophia Althammer, Ahmet Üstün +2
cs.CLcs.LGarXiv:2604.17609v12026
Measuring Digital Labour Market Transitions with a Digital Semantic Score: An AI-Based Methodology Applied to the Dutch Labour Market
Sadegh Shahmohammadi, Xavier Pinho, Mairi Bowdler +2
cs.CLarXiv:2608.24222v12026
Multi-Perspective Context Matching for Machine Comprehension
Zhiguo Wang, Haitao Mi, Wael Hamza +1
cs.CLarXiv:1612.04211v12016
Unsupervised Domain Clusters in Pretrained Language Models
Roee Aharoni, Yoav Goldberg
cs.CLarXiv:2004.02105v22020
Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems
Yiqiao Jin, Yiyang Wang, Lucheng Fu +8
cs.CLcs.AIcs.CYarXiv:2610.01257v12026
Evaluation-as-Search: Adaptive Discovery of Grounding Failures in Meeting Assistants
Sami Khairy, Yasaman Hosseinkashi, Vishak Gopal +1
cs.CLcs.AIarXiv:2608.20392v12026
Get To The Point: Summarization with Pointer-Generator Networks
Abigail See, Peter J. Liu, Christopher D. Manning
cs.CLarXiv:1704.04368v22017
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning
Weichen Dai, Rafael Medeiros Cabral, Ziyi Shou +4
cs.AIcs.CLarXiv:2609.10335v12026
AuraForge: Scaling Security Supervision for Training Coding Agents
Danqing Wang, Songwen Zhao, Harsh Sharma +4
cs.CRcs.CLcs.CYarXiv:2610.00850v12026
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
Zirui Liu, Jiayi Yuan, Hongye Jin +5
cs.CLcs.LGcs.PFarXiv:2402.02750v22024
HouseholdBench: Evaluating Large Language Models as Predictors of Household Economic Behavior
Jin Huang, Diego Ferreras Garrucho, Yutong Xie +4
cs.CLarXiv:2610.07563v12026
Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
Eric Zelikman, Eliana Lorch, Lester Mackey +1
cs.CLcs.AIcs.LGarXiv:2310.02304v32023
Constraint-Guided Enterprise Data Mapping with Large Language Models
Sebastian Monka, Pramod Anantharam, Thien Vo Minh +1
cs.AIcs.CLarXiv:2608.24218v12026
A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers
Xiaoyan Zhao, Yang Deng, Min Yang +6
cs.CLcs.AIarXiv:2306.02051v32023
UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design
Yuxuan Lu, Bingsheng Yao, Hansu Gu +7
cs.HCcs.CLarXiv:2502.12561v32025
PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation
Yunhao Liu, Hong Phuc Pham, Jaehong Yoon
cs.CLcs.AIcs.SEarXiv:2609.02272v12026
MTEB: Massive Text Embedding Benchmark
Niklas Muennighoff, Nouamane Tazi, Loïc Magne +1
cs.CLcs.IRcs.LGarXiv:2210.07316v32022
TIES-Merging: Resolving Interference When Merging Models
Prateek Yadav, Derek Tam, Leshem Choshen +2
cs.LGcs.AIcs.CLarXiv:2306.01708v22023
There Is More to Refusal in Large Language Models than a Single Direction
Faaiz Joad, Majd Hawasly, Sabri Boughorbel +2
cs.CLarXiv:2602.02132v12026
LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
Xuhao Hu, Peng Wang, Xiaoya Lu +3
cs.CLcs.AIcs.CRarXiv:2510.08211v22025
CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards
Zhuofan Chen, Ziqian Jiao, Yikai Cui +3
cs.CLcs.LGarXiv:2609.07183v12026
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
Xuefei Ning, Zinan Lin, Zixuan Zhou +3
cs.CLcs.AIarXiv:2307.15337v32023
SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution
Hanlin Wang, Chak Tou Leong, Jiashuo Wang +2
cs.CLcs.LGarXiv:2505.20732v12025
Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models
Mimo Shirasaka, Haochen Zhang, Yonatan Bisk
cs.CVcs.CLcs.LGarXiv:2609.06880v12026
Efficient and Robust Question Answering from Minimal Context over Documents
Sewon Min, Victor Zhong, Richard Socher +1
cs.CLarXiv:1805.08092v12018
Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
Xinyu Tang, Yuliang Zhan, Zhixun Li +5
cs.CLarXiv:2512.21625v12025
AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
Junyang Wang, Yuhang Wang, Guohai Xu +8
cs.CLcs.CVarXiv:2311.07397v22023
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
Matteo Pagliardini, Amirkeivan Mohtashami, Francois Fleuret +1
cs.CLcs.LGarXiv:2402.02622v22024
DeepStory: Video Story QA by Deep Embedded Memory Networks
Kyung-Min Kim, Min-Oh Heo, Seong-Ho Choi +1
cs.CVcs.AIcs.CLarXiv:1707.00836v12017
An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
Mingzhong Sun, Teresa Yeo, Armando Solar-Lezama +1
cs.AIcs.CLcs.LGarXiv:2606.01462v12026
Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems
Paweł Budzianowski, Ivan Vulić
cs.CLarXiv:1907.05774v22019
You Are What You Read: Misalignment via In-Context Persona Induction
Kyuhee Kim, Benjamin Berczi, Cozmin Ududec
cs.CLcs.AIarXiv:2609.06851v12026
Measuring GEO Visibility: Prompt Corpora Define the Answer Market
Olivier Martinez
cs.IRcs.CLarXiv:2609.06811v12026
WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects
Daniel Deutsch, Eleftheria Briakou, Isaac Caswell +14
cs.CLarXiv:2502.12404v12025
Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
Wei Zhao, Zhe Li, Yige Li +1
cs.CRcs.AIcs.CLarXiv:2410.00451v32024
Language Models are Few-Shot Learners
Tom B. Brown, Benjamin Mann, Nick Ryder +28
cs.CLarXiv:2005.14165v42020
Summaries:한국어
Preference Data Selection for Mitigating the Alignment Tax in Large Language Models
Minsu Kim, Jianxun Lian, Xing Xie +1
cs.AIcs.CLarXiv:2608.24192v12026
OAgents: An Empirical Study of Building Effective Agents
He Zhu, Tianrui Qin, King Zhu +21
cs.AIcs.CLarXiv:2506.15741v22025
DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
Xianjun Yang, Wei Cheng, Yue Wu +3
cs.CLcs.AIarXiv:2305.17359v22023
Learning to Generate Equitable Text in Dialogue from Biased Training Data
Anthony Sicilia, Malihe Alikhani
cs.CLcs.AIarXiv:2307.04303v12023
Quantifying Consonant Contributions to Word Intelligibility via Acoustic Masking
Eunjung Yeo, Kwanghee Choi, Krupaben Kothadia +4
cs.CLarXiv:2609.12122v22026
Queer People are People First: Deconstructing Sexual Identity Stereotypes in Large Language Models
Harnoor Dhingra, Preetiha Jayashanker, Sayali Moghe +1
cs.CLcs.AIarXiv:2307.00101v12023
A negation detection assessment of GPTs: analysis with the xNot360 dataset
Ha Thanh Nguyen, Randy Goebel, Francesca Toni +2
cs.CLarXiv:2306.16638v12023
PairUni: Pairwise Training for Unified Multimodal Language Models
Jiani Zheng, Zhiyang Teng, Kunpeng Qiu +6
cs.CLarXiv:2510.25682v32025
Max-Margin Token Selection in Attention Mechanism
Davoud Ataee Tarzanagh, Yingcong Li, Xuechen Zhang +1
cs.LGcs.AIcs.CLarXiv:2306.13596v42023
A Set of Recommendations for Assessing Human-Machine Parity in Language Translation
Samuel Läubli, Sheila Castilho, Graham Neubig +3
cs.CLcs.AIarXiv:2004.01694v12020
SPINE: SParse Interpretable Neural Embeddings
Anant Subramanian, Danish Pruthi, Harsh Jhamtani +2
cs.CLarXiv:1711.08792v12017
KiUT: Knowledge-injected U-Transformer for Radiology Report Generation
Zhongzhen Huang, Xiaofan Zhang, Shaoting Zhang
cs.CVcs.CLarXiv:2306.11345v12023
On the Recoverability of Private Information Unlearning in Large Language Models
Shicheng Hu, Runzhi Tian, Ziqiao Wang +1
cs.LGcs.CLarXiv:2608.29943v12026

Computation and Language

KinyaEmbed: Contrastive Sentence Embeddings for Kinyarwanda via Multi-Stage Curriculum Training

SWE-RM: Execution-free Feedback For Software Engineering Agents

Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions

Large Language Models can Strategically Deceive their Users when Put Under Pressure

Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference

#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models

Understanding Undesirable Word Embedding Associations

Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech

DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text

Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning

DarkBench: Benchmarking Dark Patterns in Large Language Models

Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity

Measuring Digital Labour Market Transitions with a Digital Semantic Score: An AI-Based Methodology Applied to the Dutch Labour Market

Multi-Perspective Context Matching for Machine Comprehension

Unsupervised Domain Clusters in Pretrained Language Models

Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems

Evaluation-as-Search: Adaptive Discovery of Grounding Failures in Meeting Assistants

Get To The Point: Summarization with Pointer-Generator Networks

From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning

AuraForge: Scaling Security Supervision for Training Coding Agents

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

HouseholdBench: Evaluating Large Language Models as Predictors of Household Economic Behavior

Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation

Constraint-Guided Enterprise Data Mapping with Large Language Models

A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers

UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design

PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation

MTEB: Massive Text Embedding Benchmark

TIES-Merging: Resolving Interference When Merging Models

There Is More to Refusal in Large Language Models than a Single Direction

LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution

Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models

Efficient and Robust Question Answering from Minimal Context over Documents

Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards

AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging

DeepStory: Video Story QA by Deep Embedded Memory Networks

An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models

Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems

You Are What You Read: Misalignment via In-Context Persona Induction

Measuring GEO Visibility: Prompt Corpora Define the Answer Market

WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialects

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models

Language Models are Few-Shot Learners

Preference Data Selection for Mitigating the Alignment Tax in Large Language Models

OAgents: An Empirical Study of Building Effective Agents

DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text

Learning to Generate Equitable Text in Dialogue from Biased Training Data

Quantifying Consonant Contributions to Word Intelligibility via Acoustic Masking

Queer People are People First: Deconstructing Sexual Identity Stereotypes in Large Language Models

A negation detection assessment of GPTs: analysis with the xNot360 dataset

PairUni: Pairwise Training for Unified Multimodal Language Models

Max-Margin Token Selection in Attention Mechanism

A Set of Recommendations for Assessing Human-Machine Parity in Language Translation

SPINE: SParse Interpretable Neural Embeddings

KiUT: Knowledge-injected U-Transformer for Radiology Report Generation

On the Recoverability of Private Information Unlearning in Large Language Models