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)

15,601 to 15,660 of 19,076

Vision-Language Models for Edge Networks: A Comprehensive Survey
Ahmed Sharshar, Latif U. Khan, Waseem Ullah +1
cs.CVcs.AIcs.CLarXiv:2502.07855v22025
An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability
David Herrera-Poyatos, Carlos Peláez-González, Cristina Zuheros +4
cs.CLcs.AIarXiv:2504.04462v12025
GANDR: Claim Auditing for Verifiable Legal Answer Generation
Chen Qian, Yimeng Wang, Yu Chen +2
cs.CLcs.AIcs.IRarXiv:2609.10293v12026
LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
Theo X. Olausson, Alex Gu, Benjamin Lipkin +4
cs.CLcs.AIarXiv:2310.15164v22023
MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis
Yihao Chen, Shi Chang, Khaled Chawa +4
cs.SEcs.CLcs.LGarXiv:2607.27146v12026
Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
Runzhe Zhan, Zhihong Huang, Xinyi Yang +3
cs.CLcs.AIarXiv:2510.20780v12025
Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback
Guijin Son, Jehyun Park, Seyeon Park +2
cs.GRcs.CLarXiv:2605.17448v22026
Exploring the Feasibility of ChatGPT for Event Extraction
Jun Gao, Huan Zhao, Changlong Yu +1
cs.CLarXiv:2303.03836v22023
Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
Guan-Ting Lin, Jiachen Lian, Tingle Li +4
cs.CLeess.ASarXiv:2503.04721v32025
Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
Matthias Gerstgrasser, Rylan Schaeffer, Apratim Dey +11
cs.LGcs.AIcs.CLarXiv:2404.01413v22024
FlashThink: An Early Exit Method For Efficient Reasoning
Guochao Jiang, Guofeng Quan, Zepeng Ding +3
cs.CLcs.AIarXiv:2505.13949v12025
Decision-Oriented Recommendation Reranking: An Empirical Study of Jev
Hanjia Lyu, Yinglong Xia
cs.IRcs.CLarXiv:2609.40241v12026
DocPrompting: Generating Code by Retrieving the Docs
Shuyan Zhou, Uri Alon, Frank F. Xu +3
cs.CLcs.AIcs.SEarXiv:2207.05987v32022
Auditing large language models: a three-layered approach
Jakob Mökander, Jonas Schuett, Hannah Rose Kirk +1
cs.CLcs.AIcs.CYarXiv:2302.08500v22023
Early science acceleration experiments with GPT-5
Sébastien Bubeck, Christian Coester, Ronen Eldan +11
cs.CLcs.AIarXiv:2511.16072v12025
Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors
Joshua Penman
cs.AIcs.CLcs.CRarXiv:2608.23873v12026
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
Selim Kuzucu, Alessio Tonioni, Vasile Lup +3
cs.CVcs.AIcs.CLarXiv:2605.30126v12026
AudioBench: A Universal Benchmark for Audio Large Language Models
Bin Wang, Xunlong Zou, Geyu Lin +6
cs.SDcs.CLeess.ASarXiv:2406.16020v52024
Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
Guanglin Niu, Yang Li, Chengguang Tang +7
cs.AIcs.CLarXiv:2104.13095v22021
When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications
Qidong Liu, Xian Wu, Xiangyu Zhao +4
cs.CLcs.AIarXiv:2310.18339v22023
An Empirical Study on Eliciting and Improving R1-like Reasoning Models
Zhipeng Chen, Yingqian Min, Beichen Zhang +10
cs.CLarXiv:2503.04548v12025
Learning Neural Templates for Text Generation
Sam Wiseman, Stuart M. Shieber, Alexander M. Rush
cs.CLcs.LGarXiv:1808.10122v32018
Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close
Rania Elbadry, Ahmed Heakl, Saeed Almheiri +12
cs.CLcs.AIcs.LGarXiv:2609.00999v12026
Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models
Jiacong Xu, Shao-Yuan Lo, Bardia Safaei +2
cs.CVcs.CLarXiv:2502.07601v22025
MTNT: A Testbed for Machine Translation of Noisy Text
Paul Michel, Graham Neubig
cs.CLarXiv:1809.00388v12018
Semantic Product Search
Priyanka Nigam, Yiwei Song, Vijai Mohan +7
cs.IRcs.CLarXiv:1907.00937v12019
LLM Judges as Raters: A Pre-Registered Audit of Severity, Halo, Reliability, and Version Instability in LLM Essay Scoring on Public Corpora
Veerendra Kumar Sunkavalli
cs.CLarXiv:2608.29517v12026
Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification
Renrui Zhang, Zhang Wei, Rongyao Fang +5
cs.CVcs.AIcs.CLarXiv:2207.09519v12022
Large Language Models in Resolving Contextual Knowledge Conflicts
Xinye Yang, Zhenyang Liu, Ruisi Li +1
cs.CLarXiv:2609.03148v12026
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Yu Sun, Shuohuan Wang, Shikun Feng +19
cs.CLarXiv:2107.02137v12021
Knowing When Not to Answer: Pseudo-Ensembles for Abstention in Music Audio-Language Models
Aanya Maheshwari, Vatsal Raina
cs.SDcs.CLarXiv:2609.04362v12026
HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks
Zhilin Wang, Jiaqi Zeng, Olivier Delalleau +6
cs.CLcs.AIcs.LGarXiv:2503.04378v22025
Unsupervised Neural Machine Translation with Weight Sharing
Zhen Yang, Wei Chen, Feng Wang +1
cs.CLarXiv:1804.09057v12018
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Yaxuan Li, Yuxin Zuo, Bingxiang He +8
cs.LGcs.AIcs.CLarXiv:2604.13016v22026
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
NVIDIA, :, Aaron Blakeman +198
cs.CLcs.AIcs.LGarXiv:2504.03624v42025
Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks
Elias Lumer, Faheem Nizar, Akshaya Jangiti +4
cs.CLarXiv:2601.06007v22026
BooookScore: A systematic exploration of book-length summarization in the era of LLMs
Yapei Chang, Kyle Lo, Tanya Goyal +1
cs.CLcs.AIcs.LGarXiv:2310.00785v42023
MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression
Youpeng Zhao, Tian Tan, Liqian Peng +2
cs.CLarXiv:2609.29913v12026
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
Marwa Abdulhai, Isadora White, Charlie Snell +5
cs.CLcs.AIcs.LGarXiv:2311.18232v12023
Latent Retrieval for Weakly Supervised Open Domain Question Answering
Kenton Lee, Ming-Wei Chang, Kristina Toutanova
cs.CLarXiv:1906.00300v32019
Out-of-Distribution Detection and Selective Generation for Conditional Language Models
Jie Ren, Jiaming Luo, Yao Zhao +4
cs.CLarXiv:2209.15558v22022
LLM2Vec-Gen: Generative Embeddings from Large Language Models
Parishad BehnamGhader, Vaibhav Adlakha, Fabian David Schmidt +3
cs.CLarXiv:2603.10913v32026
Large Language Models as Generalizable Policies for Embodied Tasks
Andrew Szot, Max Schwarzer, Harsh Agrawal +6
cs.LGcs.AIcs.CLarXiv:2310.17722v22023
CHASE: Channel-Aligned Structure Exploitation for Geometry-Aware Model Engineering
Wei Wang, Wei Jiang, Ziran Liu
cs.LGcs.CLarXiv:2610.09476v12026
Three-Phase Transformer
Mohammad R. Abu Ayyash
cs.CLcs.AIcs.LGarXiv:2604.14430v12026
Thinkless: LLM Learns When to Think
Gongfan Fang, Xinyin Ma, Xinchao Wang
cs.CLcs.AIarXiv:2505.13379v22025
TextGrad: Automatic "Differentiation" via Text
Mert Yuksekgonul, Federico Bianchi, Joseph Boen +4
cs.CLcs.AIcs.LGarXiv:2406.07496v12024
Differential Privacy for Text Analytics via Natural Text Sanitization
Xiang Yue, Minxin Du, Tianhao Wang +3
cs.CLcs.CRarXiv:2106.01221v12021
LLMs Can Generate a Better Answer by Aggregating Their Own Responses
Zichong Li, Xinyu Feng, Yuheng Cai +6
cs.CLarXiv:2503.04104v22025
Experimental Support for a Categorical Compositional Distributional Model of Meaning
Edward Grefenstette, Mehrnoosh Sadrzadeh
cs.CLmath.CTarXiv:1106.4058v12011
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Haoming Xu, Ningyuan Zhao, Yunzhi Yao +7
cs.CLcs.AIcs.HCarXiv:2601.05905v22026
OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
Chun-Wah Hsu, Kai Gong, Yu Wu +12
cs.SEcs.AIcs.CLarXiv:2609.38345v12026
Online Representation Learning in Recurrent Neural Language Models
Marek Rei
cs.CLcs.LGcs.NEarXiv:1508.03854v12015
SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
Yaosheng Fu, Guangxuan Xiao, Xin Dong +2
cs.CLcs.LGarXiv:2606.04511v12026
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Ang Li, Ben Liu, Bin Han +215
cs.CLcs.AIarXiv:2606.15079v12026
Should we Stop Training More Monolingual Models, and Simply Use Machine Translation Instead?
Tim Isbister, Fredrik Carlsson, Magnus Sahlgren
cs.CLcs.LGarXiv:2104.10441v12021
Topic Modeling Based Multi-modal Depression Detection
Yuan Gong, Christian Poellabauer
cs.CLcs.IRcs.LGarXiv:1803.10384v12018
Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering
Zihao Zhu, Jing Yu, Yujing Wang +3
cs.CVcs.AIcs.CLarXiv:2006.09073v32020
CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists
Yukyung Lee, Joonghoon Kim, Jaehee Kim +4
cs.CLarXiv:2403.18771v32024
The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models
Ronak Pradeep, Rodrigo Nogueira, Jimmy Lin
cs.IRcs.CLarXiv:2101.05667v12021

Computation and Language

Vision-Language Models for Edge Networks: A Comprehensive Survey

An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability

GANDR: Claim Auditing for Verifiable Legal Answer Generation

LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers

MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis

Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost

Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback

Exploring the Feasibility of ChatGPT for Event Extraction

Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities

Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data

FlashThink: An Early Exit Method For Efficient Reasoning

Decision-Oriented Recommendation Reranking: An Empirical Study of Jev

DocPrompting: Generating Code by Retrieving the Docs

Auditing large language models: a three-layered approach

Early science acceleration experiments with GPT-5

Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors

PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding

AudioBench: A Universal Benchmark for Audio Large Language Models

Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion

When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications

An Empirical Study on Eliciting and Improving R1-like Reasoning Models

Learning Neural Templates for Text Generation

Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close

Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models

MTNT: A Testbed for Machine Translation of Noisy Text

Semantic Product Search

LLM Judges as Raters: A Pre-Registered Audit of Severity, Halo, Reliability, and Version Instability in LLM Essay Scoring on Public Corpora

Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification

Large Language Models in Resolving Contextual Knowledge Conflicts

ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation

Knowing When Not to Answer: Pseudo-Ensembles for Abstention in Music Audio-Language Models

HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks

Unsupervised Neural Machine Translation with Weight Sharing

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks

BooookScore: A systematic exploration of book-length summarization in the era of LLMs

MILO: Efficient Many-shot In-Context Learning with Block-wise Low-rank Compression

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models

Latent Retrieval for Weakly Supervised Open Domain Question Answering

Out-of-Distribution Detection and Selective Generation for Conditional Language Models

LLM2Vec-Gen: Generative Embeddings from Large Language Models

Large Language Models as Generalizable Policies for Embodied Tasks

CHASE: Channel-Aligned Structure Exploitation for Geometry-Aware Model Engineering

Three-Phase Transformer

Thinkless: LLM Learns When to Think

TextGrad: Automatic "Differentiation" via Text

Differential Privacy for Text Analytics via Natural Text Sanitization

LLMs Can Generate a Better Answer by Aggregating Their Own Responses

Experimental Support for a Categorical Compositional Distributional Model of Meaning

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime

Online Representation Learning in Recurrent Neural Language Models

SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Should we Stop Training More Monolingual Models, and Simply Use Machine Translation Instead?

Topic Modeling Based Multi-modal Depression Detection

Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering

CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists

The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models