{"total":121,"rows":[{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463,"area":"alignment"},{"id":"2305.10425","title":"SLiC-HF: Sequence Likelihood Calibration with Human Feedback","created":"2023-05-17","cited_by_count":401,"area":"alignment"},{"id":"2309.06657","title":"Statistical Rejection Sampling Improves Preference Optimization","created":"2023-09-13","cited_by_count":323,"area":"alignment"},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291,"area":"alignment"},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"area":"alignment"},{"id":"2310.17022","title":"Controlled Decoding from Language Models","created":"2023-10-25","cited_by_count":135,"area":null},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2401.01879","title":"Theoretical guarantees on the best-of-n alignment policy","created":"2024-01-03","cited_by_count":124,"area":"lr"},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2406.00045","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","created":"2024-05-28","cited_by_count":118,"area":"alignment"},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112,"area":null},{"id":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85,"area":"alignment"},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75,"area":null},{"id":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67,"area":"alignment"},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67,"area":"alignment"},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2305.11707","title":"What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability","created":"2023-05-19","cited_by_count":51,"area":null},{"id":"2310.17918","title":"Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method","created":"2023-10-27","cited_by_count":51,"area":null},{"id":"2310.10047","title":"Improving Large Language Model Fine-tuning for Solving Math Problems","created":"2023-10-16","cited_by_count":49,"area":null},{"id":"2310.08184","title":"Learning from models beyond fine-tuning","created":"2023-10-12","cited_by_count":48,"area":null},{"id":"2405.19534","title":"Preference Learning Algorithms Do Not Learn Preference Rankings","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2404.01730","title":"Asymptotics of Language Model Alignment","created":"2024-04-02","cited_by_count":47,"area":"alignment"},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2212.10622","title":"mFACE: Multilingual Summarization with Factual Consistency Evaluation","created":"2022-12-20","cited_by_count":42,"area":null},{"id":"2410.03953","title":"LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity","created":"2024-10-04","cited_by_count":42,"area":null},{"id":"2306.03350","title":"Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning","created":"2023-06-06","cited_by_count":41,"area":null},{"id":"2404.16792","title":"Model Extrapolation Expedites Alignment","created":"2024-04-25","cited_by_count":37,"area":"alignment"},{"id":"2403.14221","title":"Improving the Robustness of Large Language Models via Consistency Alignment","created":"2024-03-21","cited_by_count":36,"area":"alignment"},{"id":"2412.19792","title":"InfAlign: Inference-aware language model alignment","created":"2024-12-27","cited_by_count":35,"area":"alignment"},{"id":"2401.12873","title":"Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model","created":"2024-01-23","cited_by_count":33,"area":"alignment"},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2310.05782","title":"Aligning Language Models with Human Preferences via a Bayesian Approach","created":"2023-10-09","cited_by_count":27,"area":"alignment"},{"id":"2406.05882","title":"Distributional Preference Alignment of LLMs via Optimal Transport","created":"2024-06-09","cited_by_count":26,"area":"alignment"},{"id":"2304.08653","title":"On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study","created":"2023-04-17","cited_by_count":25,"area":null},{"id":"2402.00742","title":"Transforming and Combining Rewards for Aligning Large Language Models","created":"2024-02-01","cited_by_count":25,"area":"alignment"},{"id":"2403.19443","title":"Mixed Preference Optimization: Reinforcement Learning with Data Selection and Better Reference Model","created":"2024-03-28","cited_by_count":25,"area":"alignment"},{"id":"2406.05883","title":"Information Theoretic Guarantees For Policy Alignment In Large Language Models","created":"2024-06-09","cited_by_count":23,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2311.14543","title":"Data-Efficient Alignment of Large Language Models with Human Feedback Through Natural Language","created":"2023-11-24","cited_by_count":22,"area":"alignment"},{"id":"2407.13709","title":"Understanding Reference Policies in Direct Preference Optimization","created":"2024-07-18","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":"2411.10914","title":"BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment","created":"2024-11-16","cited_by_count":20,"area":"alignment"},{"id":"2305.14718","title":"Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models","created":"2023-05-24","cited_by_count":17,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2404.04102","title":"ROPO: Robust Preference Optimization for Large Language Models","created":"2024-04-05","cited_by_count":16,"area":"alignment"},{"id":"2307.09254","title":"Selective Generation for Controllable Language Models","created":"2023-07-18","cited_by_count":15,"area":null},{"id":"2404.00530","title":"Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization","created":"2024-03-31","cited_by_count":15,"area":"alignment"},{"id":"2501.03884","title":"AlphaPO: Reward Shape Matters for LLM Alignment","created":"2025-01-07","cited_by_count":14,"area":"alignment"},{"id":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2305.13477","title":"Look-back Decoding for Open-Ended Text Generation","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2305.17779","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","created":"2023-05-28","cited_by_count":9,"area":null},{"id":"2402.14228","title":"COPR: Continual Human Preference Learning via Optimal Policy Regularization","created":"2024-02-22","cited_by_count":9,"area":"alignment"},{"id":"2405.00747","title":"Soft Preference Optimization: Aligning Language Models to Expert Distributions","created":"2024-04-30","cited_by_count":9,"area":"alignment"},{"id":"2212.04257","title":"Momentum Calibration for Text Generation","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2302.06784","title":"The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation","created":"2023-02-14","cited_by_count":8,"area":null},{"id":"2305.07615","title":"What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific Summarization","created":"2023-05-12","cited_by_count":8,"area":null},{"id":"2402.15300","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","created":"2024-02-23","cited_by_count":8,"area":"mllm"},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2502.14272","title":"Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models","created":"2025-02-20","cited_by_count":8,"area":"lr"},{"id":"2310.02263","title":"Automatic Pair Construction for Contrastive Post-training","created":"2023-10-03","cited_by_count":7,"area":null},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","cited_by_count":7,"area":"alignment"},{"id":"2507.05123","title":"An Evaluation of Large Language Models on Text Summarization Tasks Using Prompt Engineering Techniques","created":"2025-07-07","cited_by_count":7,"area":null},{"id":"2406.14709","title":"Factual Dialogue Summarization via Learning from Large Language Models","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2411.07773","title":"Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation","created":"2024-11-12","cited_by_count":6,"area":"rag"},{"id":"2502.12601","title":"COPU: Conformal Prediction for Uncertainty Quantification in Natural Language Generation","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2407.04185","title":"HAF-RM: A Hybrid Alignment Framework for Reward Model Training","created":"2024-07-04","cited_by_count":5,"area":"alignment"},{"id":"2409.07772","title":"Alignment with Preference Optimization Is All You Need for LLM Safety","created":"2024-09-12","cited_by_count":5,"area":"alignment"},{"id":"2410.17131","title":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","created":"2024-10-22","cited_by_count":5,"area":"alignment"},{"id":"2412.17696","title":"Understanding the Logic of Direct Preference Alignment through Logic","created":"2024-12-23","cited_by_count":5,"area":"alignment"},{"id":"2502.13674","title":"SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2505.19060","title":"UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2310.08764","title":"Calibrating Likelihoods towards Consistency in Summarization Models","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2409.17169","title":"REAL: Response Embedding-based Alignment for LLMs","created":"2024-09-17","cited_by_count":4,"area":"alignment"},{"id":"2412.15739","title":"VORD: Visual Ordinal Calibration for Mitigating Object Hallucinations in Large Vision-Language Models","created":"2024-12-20","cited_by_count":4,"area":"mllm"},{"id":"2502.06861","title":"Design Considerations in Offline Preference-based RL","created":"2025-02-08","cited_by_count":4,"area":"alignment"},{"id":"2504.18346","title":"Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review","created":"2025-04-25","cited_by_count":4,"area":null},{"id":"2505.23183","title":"Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2310.13385","title":"Tuna: Instruction Tuning using Feedback from Large Language Models","created":"2023-10-20","cited_by_count":3,"area":"alignment"},{"id":"2403.16649","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","created":"2024-03-25","cited_by_count":3,"area":"alignment"},{"id":"2405.13541","title":"Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts","created":"2024-05-22","cited_by_count":3,"area":"alignment"},{"id":"2409.19984","title":"CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Models","created":"2024-09-30","cited_by_count":3,"area":null},{"id":"2412.02125","title":"Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies","created":"2024-12-03","cited_by_count":3,"area":"alignment"},{"id":"2412.02626","title":"Time-Reversal Provides Unsupervised Feedback to LLMs","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2501.13927","title":"CRPO: Confidence-Reward Driven Preference Optimization for Machine Translation","created":"2025-01-23","cited_by_count":3,"area":"alignment"},{"id":"2502.07645","title":"From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback","created":"2025-02-11","cited_by_count":3,"area":"offlinerl"},{"id":"2506.01523","title":"Beyond RLHF: A Unified Theoretical Framework of Alignment","created":"2025-06-02","cited_by_count":3,"area":"alignment"},{"id":"2510.18913","title":"ADPO: Anchored Direct Preference Optimization","created":"2025-10-21","cited_by_count":3,"area":"alignment"}],"next_cursor":"100"}