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)

5,641 to 5,700 of 11,242

Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
Tong Che, Yanran Li, Ruixiang Zhang +4
cs.AIcs.CLcs.LGarXiv:1702.07983v12017
Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning
Tatul Danielyan, Mariam Avetisyan, Hrant Davtyan
cs.CLcs.IRarXiv:2608.29284v12026
Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs
Abdelrahman Abdallah, Mohammed Ali, Bhawna Piryani +2
cs.CLarXiv:2608.29257v12026
UrbanGPT: Spatio-Temporal Large Language Models
Zhonghang Li, Lianghao Xia, Jiabin Tang +5
cs.CLcs.AIcs.CYarXiv:2403.00813v32024
SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization
Hojae Han, Jongyoon Kim, Sanghyuk Park +7
cs.CLcs.AIarXiv:2608.29270v12026
Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation
Leandra Fichtel, Janek Prange, Henning Wachsmuth
cs.CLarXiv:2608.29215v12026
Challenges in Detoxifying Language Models
Johannes Welbl, Amelia Glaese, Jonathan Uesato +7
cs.CLcs.AIcs.CYarXiv:2109.07445v12021
Challenges for Toxic Comment Classification: An In-Depth Error Analysis
Betty van Aken, Julian Risch, Ralf Krestel +1
cs.CLarXiv:1809.07572v12018
Detecting and Repairing Hallucinations in Retrieval-Augmented Generation
Sai Krishna Reddy Mulakkayala, Niki van Stein, Aske Plaat
cs.CLcs.AIarXiv:2608.29307v12026
Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
Angeliki Lazaridou, Karl Moritz Hermann, Karl Tuyls +1
cs.AIcs.CLcs.LGarXiv:1804.03984v12018
Learning Simple Test-Time Environments for LLM Web Agents
Junxuan Li, Zijun Liu, Ziyi Huang +4
cs.CLcs.AIcs.LGarXiv:2608.29305v12026
Summarizing Videos with Attention
Jiri Fajtl, Hajar Sadeghi Sokeh, Vasileios Argyriou +2
cs.CVcs.CLcs.LGarXiv:1812.01969v22018
When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptions
Zachary Ellis, Spencer Hazel, Adam Brandt +3
cs.CLarXiv:2608.29241v12026
GenAI Against Humanity: Nefarious Applications of Generative Artificial Intelligence and Large Language Models
Emilio Ferrara
cs.CYcs.AIcs.CLarXiv:2310.00737v32023
Anchoring Speech with Semantics: A Multimodal Adapter Mechanism for Automatic Speech Recognition in Low-Resource Languages
Kuan-Tang Huang, Cheng-Yeh Yang, Chien-Chun Wang +3
cs.CLcs.SDeess.ASarXiv:2608.29239v12026
CodeGemma: Open Code Models Based on Gemma
CodeGemma Team, Heri Zhao, Jeffrey Hui +24
cs.CLcs.AIarXiv:2406.11409v22024
Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities
Millicent Ochieng, Felermino D. M. A. Ali, Elizabeth A. Ankrah +8
cs.CLcs.HCarXiv:2608.29209v12026
Toward a Cross-Lingual Romanization Ecosystem for Sinitic Languages: A Paired Mandarin-Cantonese Case Study
Zijie Zhang, Tan Lee, Yong Cao +1
cs.CLarXiv:2608.29170v12026
Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction
Jason Weston, Antoine Bordes, Oksana Yakhnenko +1
cs.CLcs.IRcs.LGarXiv:1307.7973v12013
Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
Saibo Geng, Martin Josifoski, Maxime Peyrard +1
cs.CLcs.AIcs.LGarXiv:2305.13971v62023
Sociotechnical Safety Evaluation of Generative AI Systems
Laura Weidinger, Maribeth Rauh, Nahema Marchal +10
cs.AIcs.CLcs.CYarXiv:2310.11986v22023
HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding
Dongwook Lee, Sangkwon Park, Eunwoo Song +6
cs.CLcs.AIcs.SDarXiv:2608.29120v12026
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
Yucheng Du, Xiyang Hu
cs.CLarXiv:2608.29109v12026
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
Jannik Kossen, Jiatong Han, Muhammed Razzak +3
cs.CLcs.AIcs.LGarXiv:2406.15927v12024
Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection
Yifan Xiang, Bin Liang, Yuqi Huang +2
cs.CLcs.AIarXiv:2608.29066v12026
RouteSparse: Input-Conditional Pattern Routing for Budgeted Long-Context Prefilling
Chao Zhang, Yifan Ji, Ziyan Zhang +2
cs.CLarXiv:2608.29058v12026
Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions
Jaewoo Ahn, Junseo Kim, Hyunseo Kim +4
cs.CLcs.AIcs.CVarXiv:2608.30428v12026
Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features
Keunhyeung Park, Seunguk Yu, YoungBin Kim
cs.CLarXiv:2608.28986v12026
Few-Shot Knowledge Graph Completion
Chuxu Zhang, Huaxiu Yao, Chao Huang +3
cs.CLcs.AIcs.LGarXiv:1911.11298v12019
The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era
Kiyan Rezaee
cs.CLcs.AIcs.LGarXiv:2608.28980v12026
CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions
Tsung-Han Wu, Heekyung Lee, Anya Ji +4
cs.CLcs.CVarXiv:2608.28958v12026
The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice
Jungseob Lee, Jaehyung Seo, Heuiseok Lim
cs.CLcs.AIcs.LGarXiv:2608.28930v12026
Detecting Sarcasm in Multimodal Social Platforms
Rossano Schifanella, Paloma de Juan, Joel Tetreault +1
cs.CVcs.CLcs.MMarXiv:1608.02289v12016
Verification-Aware Training for Speculative Decoding
Geonmo Gu, Byeongho Heo, HeeJae Jun +4
cs.CLarXiv:2608.30135v12026
A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability
Zhang Enyan, R. Thomas McCoy
cs.CLcs.AIarXiv:2608.29034v12026
A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
Wan-Ting Hsu, Chieh-Kai Lin, Ming-Ying Lee +3
cs.CLarXiv:1805.06266v22018
A Simple, Fast Diverse Decoding Algorithm for Neural Generation
Jiwei Li, Will Monroe, Dan Jurafsky
cs.CLarXiv:1611.08562v22016
Progressive Transformers for End-to-End Sign Language Production
Ben Saunders, Necati Cihan Camgoz, Richard Bowden
cs.CVcs.CLcs.LGarXiv:2004.14874v22020
VocalAffectBench: Evaluating Vocal Emotion Recognition in AI Audio Models
Models Luc Debaupte, Tyler Baumgartner, Brandon Tai +3
cs.CLcs.SDarXiv:2608.28932v12026
Leveraging Turn-taking Dynamics for Intent Recognition in Multi-party Conversations
Galo Castillo-López, Alexis Lombard, Gaël de Chalendar +1
cs.CLcs.LGarXiv:2608.28926v12026
Don't Make Your LLM an Evaluation Benchmark Cheater
Kun Zhou, Yutao Zhu, Zhipeng Chen +6
cs.CLcs.AIarXiv:2311.01964v12023
Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models
Sasha Boguraev, Toshiki Nakai, Kyle Mahowald +1
cs.CLarXiv:2608.28924v12026
Will we run out of data? Limits of LLM scaling based on human-generated data
Pablo Villalobos, Anson Ho, Jaime Sevilla +3
cs.LGcs.AIcs.CLarXiv:2211.04325v22022
VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition
Tyler Baumgartner, Brandon Tai, Lisa Kaelin-Martin +4
cs.CLarXiv:2608.28916v12026
Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation
Roberto I. Ono Filho
cs.CLcs.AIcs.LGarXiv:2608.28886v12026
A Hierarchical Framework for Relation Extraction with Reinforcement Learning
Ryuichi Takanobu, Tianyang Zhang, Jiexi Liu +1
cs.CLcs.IRarXiv:1811.03925v12018
A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis
Yue Mao, Yi Shen, Chao Yu +1
cs.CLcs.AIarXiv:2101.00816v22021
Variations of the Similarity Function of TextRank for Automated Summarization
Federico Barrios, Federico López, Luis Argerich +1
cs.CLcs.IRarXiv:1602.03606v12016
The Curious Case of Hallucinations in Neural Machine Translation
Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
cs.CLcs.AIcs.LGarXiv:2104.06683v12021
No Detectable Change in Side-Level WER from Prompt-Level Context: A Preregistered Ablation on a Production Oral-History Corpus
Theodore O. Cochran, Stephanie Dodson, Keith Nore
cs.CLcs.AIcs.SDarXiv:2608.28875v12026
Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops
Faeze Ghorbanpour, Constanza Fierro, Alexander Fraser +1
cs.CLarXiv:2608.28860v12026
A Unified Deep Learning Architecture for Abuse Detection
Antigoni-Maria Founta, Despoina Chatzakou, Nicolas Kourtellis +3
cs.CLcs.SIarXiv:1802.00385v22018
A rigor-matched audit of periodic-step layer skipping for efficient llm inference: conflayers versus swift, with a supplemental analysis of trained routing alternatives
Prateek Kumar Sikdar, Arpan Ghosh
cs.CLcs.AIcs.LGarXiv:2608.28846v12026
Semi-supervised Multitask Learning for Sequence Labeling
Marek Rei
cs.CLcs.LGcs.NEarXiv:1704.07156v12017
Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies
Vivian Lai, Chacha Chen, Q. Vera Liao +2
cs.AIcs.CLcs.CYarXiv:2112.11471v12021
ReVA: A Region-Aware Visual Assistant for Visually Grounded Question Answering
Anoop Senthil
cs.CLcs.CVarXiv:2608.28707v12026
Evaluating Multilingual Sentence Embeddings for Translation Error Detection:An English--Greek Contrastive Study
Eleftherios Kalogeros, Athanasios Ntalakas, Manolis Gergatsoulis +2
cs.CLarXiv:2608.28776v12026
GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon
Rajeswari Kannan, Raj Firke, Shreya Bengle +1
cs.CLcs.AIcs.PFarXiv:2608.28667v12026
TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency
Adji B. Dieng, Chong Wang, Jianfeng Gao +1
cs.CLcs.AIcs.LGarXiv:1611.01702v22016
Test-Time Scaling for Scientific Equation Discovery
Haowei Lin, Hubert Lim, Xiangyu Wang +2
cs.CLcs.AIcs.LGarXiv:2608.28660v12026

Computation and Language

Maximum-Likelihood Augmented Discrete Generative Adversarial Networks

Cloud and On-Premises Deployment of Uzbek Legal RAG via Targeted Retriever Fine-Tuning

Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs

UrbanGPT: Spatio-Temporal Large Language Models

SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization

Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation

Challenges in Detoxifying Language Models

Challenges for Toxic Comment Classification: An In-Depth Error Analysis

Detecting and Repairing Hallucinations in Retrieval-Augmented Generation

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

Learning Simple Test-Time Environments for LLM Web Agents

Summarizing Videos with Attention

When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptions

GenAI Against Humanity: Nefarious Applications of Generative Artificial Intelligence and Large Language Models

Anchoring Speech with Semantics: A Multimodal Adapter Mechanism for Automatic Speech Recognition in Low-Resource Languages

CodeGemma: Open Code Models Based on Gemma

Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities

Toward a Cross-Lingual Romanization Ecosystem for Sinitic Languages: A Paired Mandarin-Cantonese Case Study

Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction

Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning

Sociotechnical Safety Evaluation of Generative AI Systems

HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding

Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions

Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs

Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection

RouteSparse: Input-Conditional Pattern Routing for Budgeted Long-Context Prefilling

Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions

Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features

Few-Shot Knowledge Graph Completion

The Illusion of Replacement: Rethinking Specialized Machine Learning Models in the Foundation Model Era

CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions

The Hallucination Signal Is a Mean Shift: Why Simple Probes Suffice

Detecting Sarcasm in Multimodal Social Platforms

Verification-Aware Training for Speculative Decoding

A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability

A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss

A Simple, Fast Diverse Decoding Algorithm for Neural Generation

Progressive Transformers for End-to-End Sign Language Production

VocalAffectBench: Evaluating Vocal Emotion Recognition in AI Audio Models

Leveraging Turn-taking Dynamics for Intent Recognition in Multi-party Conversations

Don't Make Your LLM an Evaluation Benchmark Cheater

Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models

Will we run out of data? Limits of LLM scaling based on human-generated data

VoiceCodeBench: Evaluating Exact Structured-Token Recovery in Automatic Speech Recognition

Moving the Mean Toward the Known Good, Not Beyond It: What Inference-Time Interventions and Weight Consolidation Buy in Open-Ended Generation

A Hierarchical Framework for Relation Extraction with Reinforcement Learning

A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis

Variations of the Similarity Function of TextRank for Automated Summarization

The Curious Case of Hallucinations in Neural Machine Translation

No Detectable Change in Side-Level WER from Prompt-Level Context: A Preregistered Ablation on a Production Oral-History Corpus

Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops

A Unified Deep Learning Architecture for Abuse Detection

A rigor-matched audit of periodic-step layer skipping for efficient llm inference: conflayers versus swift, with a supplemental analysis of trained routing alternatives

Semi-supervised Multitask Learning for Sequence Labeling

Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies

ReVA: A Region-Aware Visual Assistant for Visually Grounded Question Answering

Evaluating Multilingual Sentence Embeddings for Translation Error Detection:An English--Greek Contrastive Study

GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon

TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency

Test-Time Scaling for Scientific Equation Discovery