{"total":99,"rows":[{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830,"area":null},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841,"area":null},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487,"area":null},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394,"area":null},{"id":"2305.09617","title":"Towards Expert-Level Medical Question Answering with Large Language Models","created":"2023-05-16","cited_by_count":384,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270,"area":null},{"id":"2311.09677","title":"R-Tuning: Instructing Large Language Models to Say `I Don't Know'","created":"2023-11-16","cited_by_count":111,"area":null},{"id":"2305.08809","title":"Interpretability at Scale: Identifying Causal Mechanisms in Alpaca","created":"2023-05-15","cited_by_count":103,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2305.08298","title":"Symbol tuning improves in-context learning in language models","created":"2023-05-15","cited_by_count":75,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2305.14128","title":"Dr.ICL: Demonstration-Retrieved In-context Learning","created":"2023-05-23","cited_by_count":72,"area":null},{"id":"2401.11624","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","created":"2024-01-21","cited_by_count":70,"area":null},{"id":"2310.10035","title":"Empirical Study of Zero-Shot NER with ChatGPT","created":"2023-10-16","cited_by_count":60,"area":null},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58,"area":null},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54,"area":null},{"id":"2403.14814","title":"The opportunities and risks of large language models in mental health","created":"2024-03-21","cited_by_count":54,"area":null},{"id":"2402.11917","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","created":"2024-02-19","cited_by_count":49,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2310.12418","title":"The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions","created":"2023-10-19","cited_by_count":45,"area":null},{"id":"2401.07950","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","created":"2024-01-15","cited_by_count":39,"area":null},{"id":"2404.17218","title":"Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes","created":"2024-04-26","cited_by_count":39,"area":null},{"id":"2303.05063","title":"ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction","created":"2023-03-09","cited_by_count":38,"area":null},{"id":"2310.20046","title":"Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection","created":"2023-10-30","cited_by_count":37,"area":null},{"id":"2405.18369","title":"PromptWizard: Task-Aware Prompt Optimization Framework","created":"2024-05-28","cited_by_count":36,"area":null},{"id":"2305.15444","title":"PromptNER: Prompting For Named Entity Recognition","created":"2023-05-24","cited_by_count":35,"area":null},{"id":"2311.07230","title":"How are Prompts Different in Terms of Sensitivity?","created":"2023-11-13","cited_by_count":35,"area":null},{"id":"2302.14691","title":"Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following","created":"2023-02-28","cited_by_count":33,"area":null},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2503.05388","title":"Ontology Generation using Large Language Models","created":"2025-03-07","cited_by_count":25,"area":null},{"id":"2312.14950","title":"TypeFly: Flying Drones with Large Language Model","created":"2023-12-08","cited_by_count":23,"area":null},{"id":"2405.10587","title":"RDRec: Rationale Distillation for LLM-based Recommendation","created":"2024-05-17","cited_by_count":22,"area":null},{"id":"2310.06302","title":"Selective Demonstrations for Cross-domain Text-to-SQL","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2502.06666","title":"Automatic Evaluation of Healthcare LLMs Beyond Question-Answering","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2402.07658","title":"The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Models","created":"2024-02-12","cited_by_count":18,"area":null},{"id":"2305.05138","title":"Read, Diagnose and Chat: Towards Explainable and Interactive LLMs-Augmented Depression Detection in Social Media","created":"2023-05-09","cited_by_count":16,"area":null},{"id":"2402.02212","title":"A Survey to Recent Progress Towards Understanding In-Context Learning","created":"2024-02-03","cited_by_count":14,"area":null},{"id":"2402.12976","title":"The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis","created":"2024-02-20","cited_by_count":13,"area":null},{"id":"2406.17764","title":"BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning","created":"2024-06-25","cited_by_count":13,"area":null},{"id":"2402.14558","title":"LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Survey","created":"2024-02-22","cited_by_count":12,"area":null},{"id":"2406.10382","title":"Efficient Prompting for LLM-based Generative Internet of Things","created":"2024-06-14","cited_by_count":12,"area":null},{"id":"2304.05973","title":"HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting","created":"2023-04-12","cited_by_count":11,"area":null},{"id":"2312.17115","title":"How Far Are LLMs from Believable AI? A Benchmark for Evaluating the Believability of Human Behavior Simulation","created":"2023-12-28","cited_by_count":11,"area":null},{"id":"2404.00560","title":"A Theory for Length Generalization in Learning to Reason","created":"2024-03-31","cited_by_count":11,"area":null},{"id":"2502.05610","title":"Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2402.12391","title":"Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Data","created":"2024-02-15","cited_by_count":10,"area":null},{"id":"2307.02690","title":"Scaling In-Context Demonstrations with Structured Attention","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2408.10615","title":"Enhancing Robustness in Large Language Models: Prompting for Mitigating the Impact of Irrelevant Information","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2312.08702","title":"Rational Sensibility: LLM Enhanced Empathetic Response Generation Guided by Self-presentation Theory","created":"2023-12-14","cited_by_count":7,"area":null},{"id":"2406.17304","title":"Leveraging LLMs for Dialogue Quality Measurement","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2504.16331","title":"Can Code Language Models Learn Clarification-Seeking Behaviors?","created":"2025-04-23","cited_by_count":7,"area":null},{"id":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2504.19622","title":"From Evidence to Belief: A Bayesian Epistemology Approach to Language Models","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2509.23571","title":"Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2603.17837","title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","created":"2026-03-18","cited_by_count":6,"area":null},{"id":"2305.11789","title":"Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2412.12564","title":"Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2504.17544","title":"Auditing the Ethical Logic of Generative AI Models","created":"2025-04-24","cited_by_count":5,"area":null},{"id":"2506.13253","title":"Distinct Computations Emerge From Compositional Curricula in In-Context Learning","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2311.07099","title":"Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2402.14277","title":"GATE X-E : A Challenge Set for Gender-Fair Translations from Weakly-Gendered Languages","created":"2024-02-22","cited_by_count":4,"area":null},{"id":"2404.02054","title":"Deconstructing In-Context Learning: Understanding Prompts via Corruption","created":"2024-04-02","cited_by_count":4,"area":null},{"id":"2409.12425","title":"Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2503.22040","title":"Navigating the Risks of Using Large Language Models for Text Annotation in Social Science Research","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2601.16407","title":"Jacobian Scopes: token-level causal attributions in LLMs","created":"2026-01-23","cited_by_count":4,"area":null},{"id":"2404.02650","title":"Towards detecting unanticipated bias in Large Language Models","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2502.18791","title":"Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2503.22776","title":"Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2504.21625","title":"Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2601.03783","title":"HearSay Benchmark: Do Audio LLMs Leak What They Hear?","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2601.13284","title":"Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2402.10424","title":"Pelican Soup Framework: A Theoretical Framework for Language Model Capabilities","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2403.09703","title":"Concept-aware Data Construction Improves In-context Learning of Language Models","created":"2024-03-08","cited_by_count":2,"area":null},{"id":"2409.01497","title":"DiversityMedQA: Assessing Demographic Biases in Medical Diagnosis using Large Language Models","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2411.13269","title":"Towards Specification-Driven LLM-Based Generation of Embedded Automotive Software","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2412.11923","title":"PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detection","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2502.05615","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","created":"2025-02-08","cited_by_count":2,"area":null},{"id":"2507.21099","title":"Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2305.09204","title":"The Weighted M\\\"obius Score: A Unified Framework for Feature Attribution","created":"2023-05-16","cited_by_count":1,"area":null},{"id":"2307.14298","title":"ChatGPT and Persuasive Technologies for the Management and Delivery of Personalized Recommendations in Hotel Hospitality","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2401.09984","title":"Gradable ChatGPT Translation Evaluation","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2401.15724","title":"RE-GAINS & EnChAnT: Intelligent Tool Manipulation Systems For Enhanced Query Responses","created":"2024-01-28","cited_by_count":1,"area":null},{"id":"2511.21591","title":"On the Limits of Innate Planning in Large Language Models","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.15605","title":"ToxiTwitch: Toward Emote-Aware Hybrid Moderation for Live Streaming Platforms","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2604.05775","title":"PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.09271","title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2305.13775","title":"Concept-aware Training Improves In-context Learning Ability of Language Models","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2405.11559","title":"DaVinci at SemEval-2024 Task 9: Few-shot prompting GPT-3.5 for Unconventional Reasoning","created":"2024-05-19","cited_by_count":0,"area":null},{"id":"2410.15173","title":"Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation","created":"2024-10-19","cited_by_count":0,"area":null},{"id":"2507.18902","title":"SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2509.15218","title":"LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.18854","title":"Time Travel: LLM-Assisted Semantic Behavior Localization with Git Bisect","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2602.08548","title":"How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.13239","title":"Benchmarking Zero-Shot Reasoning Approaches for Error Detection in Solidity Smart Contracts","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2604.02176","title":"Adam's Law: Textual Frequency Law on Large Language Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.27011","title":"Automatic Causal Fairness Analysis with LLM-Generated Reporting","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2608.12372","title":"Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning","created":"2026-07-20","cited_by_count":0,"area":null}],"next_cursor":null}