{"total":72,"rows":[{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"area":"synth"},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625,"area":"alignment"},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324,"area":null},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284,"area":"distill"},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224,"area":"alignment"},{"id":"2312.09244","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","created":"2023-12-14","cited_by_count":200,"area":"alignment"},{"id":"2402.05749","title":"Generalized Preference Optimization: A Unified Approach to Offline Alignment","created":"2024-02-08","cited_by_count":157,"area":"alignment"},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2311.05112","title":"A Survey of Large Language Models in Medicine: Progress, Application, and Challenge","created":"2023-11-09","cited_by_count":124,"area":null},{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107,"area":null},{"id":"2403.05612","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","created":"2024-03-08","cited_by_count":87,"area":"alignment"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2410.18252","title":"Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models","created":"2024-10-23","cited_by_count":70,"area":"alignment"},{"id":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52,"area":null},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2406.20079","title":"Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification","created":"2024-06-28","cited_by_count":44,"area":null},{"id":"2407.15762","title":"Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning","created":"2024-07-22","cited_by_count":43,"area":null},{"id":"2402.04229","title":"MusicRL: Aligning Music Generation to Human Preferences","created":"2024-02-06","cited_by_count":32,"area":"alignment"},{"id":"2310.06827","title":"Teaching Language Models to Hallucinate Less with Synthetic Tasks","created":"2023-10-10","cited_by_count":31,"area":null},{"id":"2410.13116","title":"Learning to Summarize from LLM-generated Feedback","created":"2024-10-17","cited_by_count":24,"area":"alignment"},{"id":"2503.00295","title":"Robust Multi-Objective Preference Alignment with Online DPO","created":"2025-03-01","cited_by_count":22,"area":"alignment"},{"id":"2404.19409","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning","created":"2024-04-30","cited_by_count":20,"area":"alignment"},{"id":"2406.01660","title":"Self-Improving Robust Preference Optimization","created":"2024-06-03","cited_by_count":19,"area":"alignment"},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2404.15100","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","created":"2024-04-23","cited_by_count":15,"area":"mllm"},{"id":"2410.07473","title":"Localizing Factual Inconsistencies in Attributable Text Generation","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2406.19185","title":"Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion","created":"2024-06-27","cited_by_count":13,"area":"alignment"},{"id":"2409.04421","title":"RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs","created":"2024-09-06","cited_by_count":13,"area":null},{"id":"2409.17472","title":"Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards","created":"2024-09-26","cited_by_count":12,"area":"alignment"},{"id":"2506.15068","title":"Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation","created":"2025-06-18","cited_by_count":11,"area":"alignment"},{"id":"2411.02454","title":"Graph-based Confidence Calibration for Large Language Models","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2406.07168","title":"Teaching Language Models to Self-Improve by Learning from Language Feedback","created":"2024-06-11","cited_by_count":9,"area":"alignment"},{"id":"2406.04625","title":"Key-Element-Informed sLLM Tuning for Document Summarization","created":"2024-06-07","cited_by_count":8,"area":null},{"id":"2411.08243","title":"Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset","created":"2024-11-12","cited_by_count":8,"area":null},{"id":"2409.18618","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","created":"2024-09-27","cited_by_count":7,"area":"alignment"},{"id":"2410.15116","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2310.19347","title":"Improving Factual Consistency of News Summarization by Contrastive Preference Optimization","created":"2023-10-30","cited_by_count":6,"area":"alignment"},{"id":"2402.08479","title":"Plausible Extractive Rationalization through Semi-Supervised Entailment Signal","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2406.00303","title":"Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning","created":"2024-06-01","cited_by_count":6,"area":"alignment"},{"id":"2407.01490","title":"LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2505.15291","title":"Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2404.01588","title":"Hallucination Diversity-Aware Active Learning for Text Summarization","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2408.10490","title":"Analysis of Plan-based Retrieval for Grounded Text Generation","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2310.06176","title":"Factual and Personalized Recommendations using Language Models and Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2412.11927","title":"Transparent and Coherent Procedural Mistake Detection","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2401.13246","title":"SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning","created":"2024-01-24","cited_by_count":3,"area":"lr"},{"id":"2402.12222","title":"CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation","created":"2024-02-19","cited_by_count":3,"area":null},{"id":"2408.12095","title":"uMedSum: A Unified Framework for Advancing Medical Abstractive Summarization","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2505.11081","title":"ShiQ: Bringing back Bellman to LLMs","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2510.19325","title":"Balancing Rewards in Text Summarization: Multi-Objective Reinforcement Learning via HyperVolume Optimization","created":"2025-10-22","cited_by_count":3,"area":"alignment"},{"id":"2606.18037","title":"ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2404.13246","title":"ISQA: Informative Factuality Feedback for Scientific Summarization","created":"2024-04-20","cited_by_count":2,"area":null},{"id":"2409.14065","title":"Temporally Consistent Factuality Probing for Large Language Models","created":"2024-09-21","cited_by_count":2,"area":null},{"id":"2505.20825","title":"Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation","created":"2025-05-27","cited_by_count":2,"area":"rag"},{"id":"2506.15925","title":"Reranking-based Generation for Unbiased Perspective Summarization","created":"2025-06-19","cited_by_count":2,"area":null},{"id":"2402.15162","title":"Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2409.06601","title":"LaMsS: When Large Language Models Meet Self-Skepticism","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2511.01359","title":"PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2402.08581","title":"Improving Factual Error Correction for Abstractive Summarization via Data Distillation and Conditional-generation Cloze","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2406.18245","title":"Weak Reward Model Transforms Generative Models into Robust Causal Event Extraction Systems","created":"2024-06-26","cited_by_count":0,"area":"alignment"},{"id":"2506.07479","title":"Improving Fairness of Large Language Models in Multi-document Summarization","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2507.19081","title":"Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement","created":"2025-07-25","cited_by_count":0,"area":"diffusion"},{"id":"2601.04212","title":"TrueBrief: Faithful Summarization through Small Language Models","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2602.02878","title":"Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.05605","title":"INTERACT: An AI-Driven Extended Reality Framework for Accesible Communication Featuring Real-Time Sign Language Interpretation and Emotion Recognition","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.26840","title":"Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2606.13171","title":"NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.22402","title":"Reinforcement learning to improve large language model-based automated code compliance systems","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2609.15830","title":"CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering","created":"2026-09-14","cited_by_count":0,"area":"rag"},{"id":"2610.18442","title":"Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}