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)

16,141 to 16,200 of 19,148

Factors Influencing the Surprising Instability of Word Embeddings
Laura Wendlandt, Jonathan K. Kummerfeld, Rada Mihalcea
cs.CLarXiv:1804.09692v12018
Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
Hongli Zhou, Hui Huang, Rui Zhang +5
cs.CLarXiv:2603.08091v42026
Appendix - Recommended Statistical Significance Tests for NLP Tasks
Rotem Dror, Roi Reichart
cs.CLarXiv:1809.01448v12018
ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation
Xinghao Chen, Junnan Dong, Cai Ke +8
cs.CLarXiv:2609.36722v12026
How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification
Bhanu Prakash Vangala, Sowmya Guda, Navya Vangala
cs.CLcs.LGarXiv:2609.37882v12026
Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models
Martha Lewis, Melanie Mitchell
cs.AIcs.CLarXiv:2402.08955v12024
Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
Yunxin Li, Haoyuan Shi, Baotian Hu +5
cs.CLcs.CVcs.MMarXiv:2408.09787v12024
Legal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents
Katrina Drozdov, Oliver Chen, Langston Nashold +1
cs.AIcs.CLcs.CYarXiv:2610.00609v12026
Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
Jan Ludziejewski, Maciej Pióro, Jakub Krajewski +8
cs.LGcs.AIcs.CLarXiv:2502.05172v22025
Drift Inspector: Exploring and Measuring Scientific Drift with Atomic Contribution Claims
Vsevolod Karimov, Stepan Ostarkov, Anastasia Poroshina +2
cs.CLcs.DLarXiv:2609.39710v12026
GradeTrap: Authority Cues in Images Shift VLM Judgments Despite Explicit Instructions to Ignore Them
Deep Dessai
cs.CVcs.CLcs.CYarXiv:2609.06058v12026
DPH Parser: A Bottom-Up Grammar-Driven Parser for Joint Constituency and Dependency Analysis
Hussein Ghaly
cs.CLarXiv:2609.06070v12026
Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems
Albert Sadowski, Jarosław A. Chudziak
cs.CLcs.AIarXiv:2609.05928v12026
Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
Lucas Bandarkar, Benjamin Muller, Pritish Yuvraj +4
cs.CLcs.AIcs.LGarXiv:2410.01335v22024
Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval
Eric Enouen, Sainyam Galhotra
cs.CLcs.LGarXiv:2609.38530v12026
Dissonant ballerinas and crafty carrots: a comparative multi-modal analysis of Italian brain rot
Anca Dinu, Andra-Maria Florescu, Marius Micluta-Campeanu +3
cs.CLarXiv:2610.00402v12026
Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context
Kai Ruan, Xuan Wang, Jixiang Hong +3
cs.CLcs.AIarXiv:2412.17596v42024
Probing the Creativity of Large Language Models: Can models produce divergent semantic association?
Honghua Chen, Nai Ding
cs.CLcs.LGarXiv:2310.11158v12023
LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Prediction
Meiyun Wang, Kiyoshi Izumi, Hiroki Sakaji
cs.CLcs.AIcs.CEarXiv:2406.10811v12024
Not All Neural Embeddings are Born Equal
Felix Hill, KyungHyun Cho, Sebastien Jean +2
cs.CLarXiv:1410.0718v22014
Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best-Worst Scaling
Svetlana Kiritchenko, Saif M. Mohammad
cs.CLarXiv:1712.01741v12017
Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigations
Ismael T. Freire, Marceau Nahon, Maud van Lier +6
cs.CYcs.CLcs.HCarXiv:2609.38486v12026
Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations
Bingsheng Yao, Prithviraj Sen, Lucian Popa +2
cs.CLarXiv:2305.03117v22023
Post Hoc Explanations of Language Models Can Improve Language Models
Satyapriya Krishna, Jiaqi Ma, Dylan Slack +3
cs.CLcs.AIarXiv:2305.11426v32023
AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
Patara Trirat, Wonyong Jeong, Sung Ju Hwang
cs.LGcs.AIcs.CLarXiv:2410.02958v22024
On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition
Kazuki Irie, Rohit Prabhavalkar, Anjuli Kannan +3
cs.CLarXiv:1902.01955v22019
Streaming End-to-End Bilingual ASR Systems with Joint Language Identification
Surabhi Punjabi, Harish Arsikere, Zeynab Raeesy +11
eess.AScs.CLcs.SDarXiv:2007.03900v12020
Do Large Language Models Understand Logic or Just Mimick Context?
Junbing Yan, Chengyu Wang, Jun Huang +1
cs.CLcs.AIarXiv:2402.12091v12024
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
Duolin Sun, Dan Yang, Yue Shen +7
cs.CLcs.AIarXiv:2509.09713v12025
Graph Neural Prompting with Large Language Models
Yijun Tian, Huan Song, Zichen Wang +5
cs.CLcs.AIcs.LGarXiv:2309.15427v22023
ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims
Anirban Saha Anik, Md Fahimul Kabir Chowdhury, Andrew Wyckoff +1
cs.CLcs.AIarXiv:2509.11492v12025
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments
Project Apertus, Alejandro Hernández-Cano, Alexander Hägele +100
cs.CLcs.AIcs.LGarXiv:2509.14233v22025
Persuasive Natural Language Generation -- A Literature Review
Sebastian Duerr, Peter A. Gloor
cs.CLcs.AIarXiv:2101.05786v12021
Synthetic bootstrapped pretraining
Zitong Yang, Aonan Zhang, Hong Liu +4
cs.CLcs.AIarXiv:2509.15248v32025
Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech
Taesoo Kim, Yongsik Jo, Hyunmin Song +1
cs.HCcs.AIcs.CLarXiv:2509.14627v12025
Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Task
Allyson Ettinger, Sudha Rao, Hal Daumé III +1
cs.CLarXiv:1711.01505v12017
AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?
Hyunjong Ok, Suho Yoo, Hyeonjun Kim +1
cs.CLcs.AIcs.LGarXiv:2509.17641v22025
Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications
Selva Taş, Mahmut El Huseyni, Özay Ezerceli +2
cs.CLcs.AIarXiv:2509.17671v12025
Cross-Attention is Half Explanation in Speech-to-Text Models
Sara Papi, Dennis Fucci, Marco Gaido +2
cs.CLcs.AIcs.SDarXiv:2509.18010v22025
CompLLM: Compression for Long Context Q&A
Gabriele Berton, Jayakrishnan Unnikrishnan, Son Tran +1
cs.CLarXiv:2509.19228v22025
Degendering Resumes for Fair Algorithmic Resume Screening
Prasanna Parasurama, João Sedoc
cs.CLcs.CYarXiv:2112.08910v32021
ADAM: A Diverse Archive of Mankind for Evaluating and Enhancing LLMs in Biographical Reasoning
Jasin Cekinmez, Omid Ghahroodi, Saad Fowad Chandle +2
cs.CLcs.AIcs.CVarXiv:2509.22991v12025
From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs
Haonan Wang, Weida Liang, Zihang Fu +8
cs.CLarXiv:2509.23196v12025
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
Wenhua Cheng, Weiwei Zhang, Haihao Shen +4
cs.CLcs.AIcs.LGarXiv:2309.05516v52023
AlignBench: Benchmarking Chinese Alignment of Large Language Models
Xiao Liu, Xuanyu Lei, Shengyuan Wang +15
cs.CLcs.AIcs.LGarXiv:2311.18743v42023
Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
Xin Xu, Cliveb AI, Kai Yang +4
cs.LGcs.CLarXiv:2509.26226v22025
OceanGym: A Benchmark Environment for Underwater Embodied Agents
Yida Xue, Mingjun Mao, Xiangyuan Ru +9
cs.CLcs.AIcs.CVarXiv:2509.26536v32025
TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics
Yi-Cheng Lin, Yu-Hua Chen, Jia-Kai Dong +12
eess.AScs.CLcs.LGarXiv:2509.26329v12025
Co-Linguistics: AI-augmented Theory Construction in Linguistics
Emmanuel Chemla, Benjamin Spector, Alexandros Kalomoiros +1
cs.CLarXiv:2609.37635v12026
Direct Multi-Token Decoding
Xuan Luo, Weizhi Wang, Xifeng Yan
cs.CLcs.AIarXiv:2510.11958v12025
Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contexts
Perapard Ngokpol, Kun Kerdthaisong, Pasin Buakhaw +4
cs.CLcs.AIarXiv:2510.14351v22025
The Atomic Instruction Gap: Instruction-Tuned LLMs Struggle with Simple, Self-Contained Directives
Henry Lim, Kwan Hui Lim
cs.CLarXiv:2510.17388v12025
The Natural Stories Corpus
Richard Futrell, Edward Gibson, Hal Tily +4
cs.CLarXiv:1708.05763v12017
MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories
Minjin Choi, Sunkyung Lee, Eunseong Choi +4
cs.CLcs.LGarXiv:2104.13615v12021
UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding
Hao Feng, Zijian Wang, Jingqun Tang +4
cs.AIcs.CLarXiv:2308.11592v22023
ManyModalQA: Modality Disambiguation and QA over Diverse Inputs
Darryl Hannan, Akshay Jain, Mohit Bansal
cs.CLcs.AIcs.CVarXiv:2001.08034v12020
VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models
Chenyu Zhou, Mengdan Zhang, Peixian Chen +5
cs.CVcs.AIcs.CLarXiv:2406.10228v12024
Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation
Antonela Tommasel, Markus Schedl
cs.CLarXiv:2610.00070v12026
Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing
Pakorn Nathong, Kunat Pipatanakul
cs.DCcs.AIcs.CLarXiv:2610.00063v12026
The First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating
Gnaneswar Villuri, Hashmath Shaik, Alex Doboli
cs.CLcs.AIarXiv:2610.00054v12026

Computation and Language

Factors Influencing the Surprising Instability of Word Embeddings

Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization

Appendix - Recommended Statistical Significance Tests for NLP Tasks

ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptation

How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification

Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models

Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation

Legal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents

Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient

Drift Inspector: Exploring and Measuring Scientific Drift with Atomic Contribution Claims

GradeTrap: Authority Cues in Images Shift VLM Judgments Despite Explicit Instructions to Ignore Them

DPH Parser: A Bottom-Up Grammar-Driven Parser for Joint Constituency and Dependency Analysis

Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems

Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models

Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval

Dissonant ballerinas and crafty carrots: a comparative multi-modal analysis of Italian brain rot

Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context

Probing the Creativity of Large Language Models: Can models produce divergent semantic association?

LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Prediction

Not All Neural Embeddings are Born Equal

Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best-Worst Scaling

Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigations

Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations

Post Hoc Explanations of Language Models Can Improve Language Models

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition

Streaming End-to-End Bilingual ASR Systems with Joint Language Identification

Do Large Language Models Understand Logic or Just Mimick Context?

HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering

Graph Neural Prompting with Large Language Models

ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Persuasive Natural Language Generation -- A Literature Review

Synthetic bootstrapped pretraining

Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech

Towards Linguistically Generalizable NLP Systems: A Workshop and Shared Task

AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?

Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications

Cross-Attention is Half Explanation in Speech-to-Text Models

CompLLM: Compression for Long Context Q&A

Degendering Resumes for Fair Algorithmic Resume Screening

ADAM: A Diverse Archive of Mankind for Evaluating and Enhancing LLMs in Biographical Reasoning

From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs

AlignBench: Benchmarking Chinese Alignment of Large Language Models

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners

OceanGym: A Benchmark Environment for Underwater Embodied Agents

TAU: A Benchmark for Cultural Sound Understanding Beyond Semantics

Co-Linguistics: AI-augmented Theory Construction in Linguistics

Direct Multi-Token Decoding

Beyond One World: Benchmarking Super Heros in Role-Playing Across Multiversal Contexts

The Atomic Instruction Gap: Instruction-Tuned LLMs Struggle with Simple, Self-Contained Directives

The Natural Stories Corpus

MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories

UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding

ManyModalQA: Modality Disambiguation and QA over Diverse Inputs

VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models

Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation

Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing

The First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating