{"total":270,"rows":[{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839,"area":"rag"},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560,"area":"safety"},{"id":"2308.06463","title":"GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher","created":"2023-08-12","cited_by_count":423,"area":"alignment"},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309,"area":"safety"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240,"area":"safety"},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229,"area":null},{"id":"2310.19736","title":"Evaluating Large Language Models: A Comprehensive Survey","created":"2023-10-30","cited_by_count":202,"area":null},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189,"area":null},{"id":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176,"area":null},{"id":"2309.14556","title":"Art or Artifice? Large Language Models and the False Promise of Creativity","created":"2023-09-25","cited_by_count":172,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2310.13988","title":"GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4","created":"2023-10-21","cited_by_count":146,"area":null},{"id":"2404.12272","title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","created":"2024-04-18","cited_by_count":144,"area":"alignment"},{"id":"2402.10176","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","created":"2024-02-15","cited_by_count":143,"area":"lr"},{"id":"2309.07930","title":"Generative AI","created":"2023-09-13","cited_by_count":120,"area":null},{"id":"2307.16513","title":"Deception Abilities Emerged in Large Language Models","created":"2023-07-31","cited_by_count":101,"area":null},{"id":"2308.06077","title":"Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling","created":"2023-08-11","cited_by_count":95,"area":null},{"id":"2308.15197","title":"Where Would I Go Next? Large Language Models as Human Mobility Predictors","created":"2023-08-29","cited_by_count":93,"area":null},{"id":"2407.04069","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","created":"2024-07-04","cited_by_count":85,"area":null},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2310.01432","title":"Split and Merge: Aligning Position Biases in LLM-based Evaluators","created":"2023-09-29","cited_by_count":72,"area":null},{"id":"2311.16119","title":"Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition","created":"2023-10-24","cited_by_count":68,"area":"safety"},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"id":"2502.13295","title":"Demonstrating specification gaming in reasoning models","created":"2025-02-18","cited_by_count":56,"area":"lr"},{"id":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54,"area":"safety"},{"id":"2310.20320","title":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","created":"2023-10-31","cited_by_count":48,"area":null},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2402.18050","title":"MEGAnno+: A Human-LLM Collaborative Annotation System","created":"2024-02-28","cited_by_count":47,"area":null},{"id":"2308.06013","title":"Large Language Models for Telecom: Forthcoming Impact on the Industry","created":"2023-08-11","cited_by_count":44,"area":null},{"id":"2401.07102","title":"Evolving Code with A Large Language Model","created":"2024-01-13","cited_by_count":43,"area":null},{"id":"2308.01284","title":"Fighting Fire with Fire: Can ChatGPT Detect AI-generated Text?","created":"2023-08-02","cited_by_count":39,"area":null},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","cited_by_count":39,"area":"alignment"},{"id":"2504.04715","title":"Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs","created":"2025-04-07","cited_by_count":38,"area":null},{"id":"2310.03965","title":"Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models","created":"2023-10-06","cited_by_count":37,"area":"lr"},{"id":"2405.16122","title":"Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars","created":"2024-05-25","cited_by_count":37,"area":null},{"id":"2402.05129","title":"Best Practices for Text Annotation with Large Language Models","created":"2024-02-05","cited_by_count":36,"area":null},{"id":"2409.00598","title":"Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models","created":"2024-09-01","cited_by_count":35,"area":"alignment"},{"id":"2308.02575","title":"Is GPT-4 a reliable rater? Evaluating Consistency in GPT-4 Text Ratings","created":"2023-08-03","cited_by_count":34,"area":null},{"id":"2308.10092","title":"Open, Closed, or Small Language Models for Text Classification?","created":"2023-08-19","cited_by_count":34,"area":null},{"id":"2403.15852","title":"SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents","created":"2024-03-23","cited_by_count":34,"area":"agents"},{"id":"2308.00304","title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","created":"2023-08-01","cited_by_count":33,"area":null},{"id":"2505.13360","title":"What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts","created":"2025-05-19","cited_by_count":32,"area":null},{"id":"2311.17330","title":"Biomedical knowledge graph-optimized prompt generation for large language models","created":"2023-11-29","cited_by_count":31,"area":null},{"id":"2410.06107","title":"Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap","created":"2024-10-08","cited_by_count":30,"area":null},{"id":"2504.00025","title":"Generalization Bias in Large Language Model Summarization of Scientific Research","created":"2025-03-28","cited_by_count":30,"area":null},{"id":"2307.15770","title":"CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools","created":"2023-07-28","cited_by_count":29,"area":null},{"id":"2401.01989","title":"Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2310.12902","title":"Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling","created":"2023-10-19","cited_by_count":27,"area":null},{"id":"2404.02935","title":"KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking","created":"2024-04-03","cited_by_count":26,"area":"lr"},{"id":"2309.13356","title":"Probing the Moral Development of Large Language Models through Defining Issues Test","created":"2023-09-23","cited_by_count":25,"area":"lr"},{"id":"2311.08838","title":"Disinformation Capabilities of Large Language Models","created":"2023-11-15","cited_by_count":25,"area":null},{"id":"2405.05378","title":"\"They are uncultured\": Unveiling Covert Harms and Social Threats in LLM Generated Conversations","created":"2024-05-08","cited_by_count":25,"area":null},{"id":"2406.17633","title":"Knowledge Distillation in Automated Annotation: Supervised Text Classification with LLM-Generated Training Labels","created":"2024-06-25","cited_by_count":25,"area":"distill"},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2503.11509","title":"TikZero: Zero-Shot Text-Guided Graphics Program Synthesis","created":"2025-03-14","cited_by_count":24,"area":null},{"id":"2311.11123","title":"(Why) Is My Prompt Getting Worse? Rethinking Regression Testing for Evolving LLM APIs","created":"2023-11-18","cited_by_count":23,"area":"lr"},{"id":"2406.17675","title":"Evaluating Large Language Models with Psychometrics","created":"2024-06-25","cited_by_count":22,"area":null},{"id":"2309.00087","title":"Large language models in medicine: the potentials and pitfalls","created":"2023-08-31","cited_by_count":21,"area":null},{"id":"2506.08584","title":"CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmarking of Large Language Models in Mental Health Question Answering","created":"2025-06-10","cited_by_count":21,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2310.19671","title":"Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding","created":"2023-10-30","cited_by_count":20,"area":null},{"id":"2308.04445","title":"Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyc","created":"2023-07-31","cited_by_count":19,"area":null},{"id":"2309.04142","title":"Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2310.13712","title":"Impact of Guidance and Interaction Strategies for LLM Use on Learner Performance and Perception","created":"2023-10-13","cited_by_count":19,"area":null},{"id":"2401.03038","title":"SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines","created":"2024-01-05","cited_by_count":19,"area":"synth"},{"id":"2409.12447","title":"Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts","created":"2024-09-19","cited_by_count":19,"area":null},{"id":"2308.12086","title":"Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments","created":"2023-08-23","cited_by_count":18,"area":null},{"id":"2309.01715","title":"Prompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy Construction","created":"2023-09-04","cited_by_count":18,"area":null},{"id":"2408.14307","title":"LLM-3D Print: Large Language Models To Monitor and Control 3D Printing","created":"2024-08-26","cited_by_count":18,"area":null},{"id":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2506.06975","title":"Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2402.01108","title":"Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions","created":"2024-02-02","cited_by_count":17,"area":"lr"},{"id":"2404.02491","title":"Measuring Social Norms of Large Language Models","created":"2024-04-03","cited_by_count":17,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2409.09467","title":"Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI","created":"2024-09-14","cited_by_count":17,"area":null},{"id":"2409.14729","title":"PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs","created":"2024-09-23","cited_by_count":17,"area":"safety"},{"id":"2308.06088","title":"Assessing Student Errors in Experimentation Using Artificial Intelligence and Large Language Models: A Comparative Study with Human Raters","created":"2023-08-11","cited_by_count":16,"area":null},{"id":"2401.10186","title":"Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation","created":"2024-01-18","cited_by_count":16,"area":null},{"id":"2402.02675","title":"Verifiable evaluations of machine learning models using zkSNARKs","created":"2024-02-05","cited_by_count":16,"area":null},{"id":"2502.11019","title":"Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2310.18208","title":"ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2512.17843","title":"ShareChat: A Dataset of Chatbot Conversations in the Wild","created":"2025-12-19","cited_by_count":15,"area":null},{"id":"2309.14517","title":"Watch Your Language: Investigating Content Moderation with Large Language Models","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2309.17447","title":"A Large Language Model Approach to Educational Survey Feedback Analysis","created":"2023-09-29","cited_by_count":14,"area":null},{"id":"2311.13133","title":"LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms","created":"2023-11-22","cited_by_count":14,"area":null},{"id":"2401.15127","title":"Evaluation of LLM Chatbots for OSINT-based Cyber Threat Awareness","created":"2024-01-26","cited_by_count":14,"area":null},{"id":"2402.01656","title":"Promises and pitfalls of artificial intelligence for legal applications","created":"2024-01-10","cited_by_count":14,"area":null},{"id":"2402.03099","title":"Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2502.16169","title":"Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations","created":"2025-02-22","cited_by_count":12,"area":"lr"},{"id":"2510.25506","title":"Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2404.00486","title":"Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs","created":"2024-03-30","cited_by_count":11,"area":"alignment"},{"id":"2506.06166","title":"The Lock-in Hypothesis: Stagnation by Algorithm","created":"2025-06-06","cited_by_count":11,"area":null},{"id":"2512.10169","title":"The 2025 Foundation Model Transparency Index","created":"2025-12-11","cited_by_count":11,"area":null},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2402.15951","title":"DetoxLLM: A Framework for Detoxification with Explanations","created":"2024-02-25","cited_by_count":10,"area":null},{"id":"2404.05213","title":"Evaluation of an LLM in Identifying Logical Fallacies: A Call for Rigor When Adopting LLMs in HCI Research","created":"2024-04-08","cited_by_count":10,"area":null}],"next_cursor":"100"}