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)

781 to 840 of 11,199

Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data
Atindra Jha, Margaret Li, Jure Leskovec +2
cs.LGcs.CLarXiv:2609.11917v12026
Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens
Carl Edwards, Edward De Brouwer, Xiner Li +5
q-bio.QMcs.AIcs.CLarXiv:2609.11877v12026
Abstraction Agent
Boning Li, Longbo Huang
cs.MAcs.AIcs.CLarXiv:2609.04303v12026
BERT for Evidence Retrieval and Claim Verification
Amir Soleimani, Christof Monz, Marcel Worring
cs.CLarXiv:1910.02655v12019
RetroThinker: Enabling Retrospective Thinking in Speech LLMs
Yi-Jen Shih, Puyuan Peng, Abdelrahman Mohamed +1
eess.AScs.AIcs.CLarXiv:2609.11864v12026
A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients
Suwan Wu, Yumeng Lin, Pengcheng Yuan +1
cs.AIcs.CLcs.LGarXiv:2609.11768v12026
SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control
Suwan Wu, Yumeng Lin, Pengcheng Yuan +1
cs.AIcs.CLcs.LGarXiv:2609.11752v12026
A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations
Md Tahmid Rahman Laskar, Sawsan Alqahtani, M Saiful Bari +10
cs.CLcs.AIcs.LGarXiv:2407.04069v22024
The Semantic Elevation Operator and the Closure of the Undecidable Class under Preservation
Jose Pascual Gumbau Mezquita
cs.LOcs.AIcs.CLarXiv:2609.11326v12026
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Yi Duan, Ying Liu, Zirui Tang +30
cs.LGcs.AIcs.CLarXiv:2609.11873v12026
SpecGuard: Inference-Time Backdoor Detection For Free
Rui Wen, Ahmed Salem, Andrew Paverd +2
cs.CRcs.CLarXiv:2609.11799v12026
Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset
Dan Su, Kezhi Kong, Ying Lin +6
cs.CLarXiv:2412.02595v22024
Neural Segmental Hypergraphs for Overlapping Mention Recognition
Bailin Wang, Wei Lu
cs.CLarXiv:1810.01817v12018
Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding
Michael Picheny
eess.AScs.CLarXiv:2609.11772v12026
InFoBench: Evaluating Instruction Following Ability in Large Language Models
Yiwei Qin, Kaiqiang Song, Yebowen Hu +7
cs.CLcs.AIarXiv:2401.03601v12024
A Large-Scale Chinese Short-Text Conversation Dataset
Yida Wang, Pei Ke, Yinhe Zheng +4
cs.CLarXiv:2008.03946v22020
Why Does Post-Training Quantization Work?
Yuxiang Chen, Michael Beyer, Jun Zhu +1
cs.LGcs.CLarXiv:2609.11716v12026
Survey on reinforcement learning for language processing
Victor Uc-Cetina, Nicolas Navarro-Guerrero, Anabel Martin-Gonzalez +2
cs.CLcs.AIcs.LGarXiv:2104.05565v32021
VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents
Peiyuan Gao, Gaoyuan Zhang, Haojie Qin +5
cs.IRcs.AIcs.CLarXiv:2609.11390v12026
Xiaomi-CocktailASR-1 Technical Report
Yiru Zhang, Hang Su, Lichun Fan +10
cs.SDcs.CLeess.ASarXiv:2609.11274v12026
(Whose defaults?) Is artificial intelligence reorienting archaeological methods?
Lorenzo Cardarelli, Roberto Ragno
cs.CYcs.AIcs.CLarXiv:2609.11198v12026
LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry
Sankar Behera, Dhruv Singh, Anshika Agnihotri +3
cs.LGcs.CLarXiv:2609.11163v12026
Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks
Matthias Plappert, Christian Mandery, Tamim Asfour
cs.LGcs.CLcs.ROarXiv:1705.06400v22017
Learning to Parse and Translate Improves Neural Machine Translation
Akiko Eriguchi, Yoshimasa Tsuruoka, Kyunghyun Cho
cs.CLarXiv:1702.03525v22017
INDRA: A New AI Tool for Exploring Tobacco, Fossil Fuel, and Chemical Industry Archives
Daniel Akselrad, Robert N. Proctor
cs.DLcs.CLcs.CYarXiv:2609.11261v12026
MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions
Antoine Saillenfest
cs.LGcs.CLarXiv:2609.11253v12026
A Voice-Interactive Multi-Agent System for Smart Operating Rooms: Architecture Design and Key Technologies
Tianxiang Zhou
cs.AIcs.CLcs.HCarXiv:2609.11231v12026
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
Tuan Nguyen, Qiran Hu, Banruo Liu +3
cs.LGcs.CLcs.IRarXiv:2609.11209v12026
ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models
Qijiong Liu, Nuo Chen, Tetsuya Sakai +1
cs.IRcs.CLarXiv:2305.06566v42023
FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model
Feijie Wu, Zitao Li, Yaliang Li +2
cs.LGcs.CLcs.DCarXiv:2406.17706v12024
The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems
Yangze Liu, Zhongyi Han
cs.AIcs.CLcs.LGarXiv:2609.11146v12026
Same Day, Same Story; One Day Ahead, a Different Signal: The Dual Validity of Financial Sentiment
AS Aravinthkakshan, Laven Srivastava, Harsh Nandwani
cs.AIcs.CLcs.SIarXiv:2609.11144v12026
The information geometry of large language models is shared, learned, and controllable
Dario Picozzi
cs.LGcs.CLarXiv:2609.11063v12026
ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review
Sunder Ali Khowaja, Parus Khuwaja, Kapal Dev +2
cs.CYcs.AIcs.CLarXiv:2305.03123v42023
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble
Jorio Cocola, Lev McKinney, Harry Mayne +2
cs.LGcs.AIcs.CLarXiv:2609.10883v12026
Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation
Alireza Salemi, Surya Kallumadi, Hamed Zamani
cs.CLcs.IRarXiv:2404.05970v12024
BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation
Karish Gupta, Matthew Alex, Alex Li +6
cs.CVcs.CLarXiv:2609.10815v12026
More than half of recent astronomy papers are written with language-model assistance
Serat M. Saad, Yuan-Sen Ting
astro-ph.IMcs.CLcs.DLarXiv:2609.10664v12026
KuaiRP Series Role-playing Models Technical Report
Yipeng Wang, Ziwei Zhang, Jiahui Zhang +2
cs.AIcs.CLarXiv:2609.11127v12026
Beyond Solver Verdicts: Generative Reward Models for Autoformalization
Vikash Singh, Debargha Ganguly, Aman Goel +5
cs.LGcs.CLarXiv:2609.11085v12026
Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty
Kaitlyn Zhou, Jena D. Hwang, Xiang Ren +1
cs.CLcs.AIcs.HCarXiv:2401.06730v22024
New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models
Sourajit Saha, Shubhashis Roy Dipta, Nobin Sarwar +4
cs.CVcs.AIcs.CLarXiv:2609.11022v12026
Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2
William Novak, Muhammad Abusaqer
cs.CRcs.CLcs.LGarXiv:2609.10935v12026
Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model
Hind Saleh, Areej Alhothali, Kawthar Moria
cs.CLarXiv:2111.01515v12021
Studying Without a Syllabus: Task-Agnostic Environment Preprocessing
Vinay Samuel, Varun Ursekar, Vijay S. Kalmath +3
cs.AIcs.CLcs.LGarXiv:2609.10824v12026
The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes
Dylan Jayabahu
cs.LGcs.AIcs.CLarXiv:2609.10739v12026
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
Zonglin Li, Chong You, Srinadh Bhojanapalli +8
cs.LGcs.CLcs.CVarXiv:2210.06313v22022
Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
Tao Shen, Tianyi Zhou, Guodong Long +2
cs.CLcs.AIarXiv:1804.00857v12018
Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA
Minzheng Wang, Longze Chen, Cheng Fu +11
cs.CLcs.AIarXiv:2406.17419v22024
IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing
Pruthwik Mishra, Rudra Trivedi, Avi Patel +2
cs.CLarXiv:2609.11851v12026
Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif +2
cs.CLarXiv:2609.11838v12026
Probing Natural Language Inference Models through Semantic Fragments
Kyle Richardson, Hai Hu, Lawrence S. Moss +1
cs.CLarXiv:1909.07521v22019
Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech
Chibuzor Okocha, Christan Earl Grant
cs.CLcs.AIarXiv:2609.11786v12026
Distance generalization in transformers: why bother with positional encoding?
Daniel Henrik Nevermann, Claudius Gros
cs.CLarXiv:2609.11913v12026
Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
Yingzhi Wang, Reem Alhazzani, Muhammad Alqurishi
cs.CLarXiv:2609.11892v12026
Domain-Specific Hallucination Detection in Large Language Models
Varun Teja Chundru, Debasmita Biswas
cs.CLcs.AIcs.LGarXiv:2609.11878v12026
Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
Lisa Bylinina
cs.CLarXiv:2609.11870v12026
Epistemic orientation predicts legislative effectiveness among members of the US Congress
Segun Aroyehun, Stephan Lewandowsky, David Garcia
cs.CLarXiv:2609.11865v12026
AnglE-optimized Text Embeddings
Xianming Li, Jing Li
cs.CLcs.AIcs.LGarXiv:2309.12871v92023
The widening evaluation gap in medical large language model research 2023 to 2026
Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif
cs.CLarXiv:2609.11770v12026

Computation and Language

Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data

Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens

Abstraction Agent

BERT for Evidence Retrieval and Claim Verification

RetroThinker: Enabling Retrospective Thinking in Speech LLMs

A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients

SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control

A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations

The Semantic Elevation Operator and the Closure of the Undecidable Class under Preservation

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

SpecGuard: Inference-Time Backdoor Detection For Free

Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset

Neural Segmental Hypergraphs for Overlapping Mention Recognition

Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding

InFoBench: Evaluating Instruction Following Ability in Large Language Models

A Large-Scale Chinese Short-Text Conversation Dataset

Why Does Post-Training Quantization Work?

Survey on reinforcement learning for language processing

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

Xiaomi-CocktailASR-1 Technical Report

(Whose defaults?) Is artificial intelligence reorienting archaeological methods?

LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry

Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks

Learning to Parse and Translate Improves Neural Machine Translation

INDRA: A New AI Tool for Exploring Tobacco, Fossil Fuel, and Chemical Industry Archives

MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions

A Voice-Interactive Multi-Agent System for Smart Operating Rooms: Architecture Design and Key Technologies

REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving

ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models

FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model

The Oligarch Barely Steers Model Collapse in Multi-Model Ecosystems

Same Day, Same Story; One Day Ahead, a Different Signal: The Dual Validity of Financial Sentiment

The information geometry of large language models is shared, learned, and controllable

ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review

Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble

Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation

BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation

More than half of recent astronomy papers are written with language-model assistance

KuaiRP Series Role-playing Models Technical Report

Beyond Solver Verdicts: Generative Reward Models for Autoformalization

Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty

New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models

Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2

Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model

Studying Without a Syllabus: Task-Agnostic Environment Preprocessing

The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes

The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers

Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA

IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing

Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models

Probing Natural Language Inference Models through Semantic Fragments

Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech

Distance generalization in transformers: why bother with positional encoding?

Nuha-Speech: Building General-Purpose Arabic Speech-LLMs

Domain-Specific Hallucination Detection in Large Language Models

Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model

Epistemic orientation predicts legislative effectiveness among members of the US Congress

AnglE-optimized Text Embeddings

The widening evaluation gap in medical large language model research 2023 to 2026