{"total":100,"rows":[{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"area":"alignment"},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499,"area":"alignment"},{"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":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401,"area":"alignment"},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396,"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":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2310.03708","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","created":"2023-10-05","cited_by_count":124,"area":"alignment"},{"id":"2308.03549","title":"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue","created":"2023-08-07","cited_by_count":119,"area":"alignment"},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"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":"2402.00782","title":"Dense Reward for Free in Reinforcement Learning from Human Feedback","created":"2024-02-01","cited_by_count":78,"area":"alignment"},{"id":"2312.15997","title":"Aligning Large Language Models with Human Preferences through Representation Engineering","created":"2023-12-26","cited_by_count":71,"area":"alignment"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2402.02992","title":"Decoding-time Realignment of Language Models","created":"2024-02-05","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":"2310.00212","title":"Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment","created":"2023-09-30","cited_by_count":57,"area":"alignment"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"area":"alignment"},{"id":"2405.06639","title":"Value Augmented Sampling for Language Model Alignment and Personalization","created":"2024-05-10","cited_by_count":49,"area":"alignment"},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48,"area":"alignment"},{"id":"2405.19534","title":"Preference Learning Algorithms Do Not Learn Preference Rankings","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"area":"alignment"},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"area":"alignment"},{"id":"2406.05534","title":"Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing","created":"2024-06-08","cited_by_count":39,"area":"alignment"},{"id":"2505.20065","title":"SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety","created":"2025-05-26","cited_by_count":37,"area":"alignment"},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"id":"2402.10958","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","created":"2024-02-12","cited_by_count":36,"area":"alignment"},{"id":"2311.04072","title":"Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment","created":"2023-11-07","cited_by_count":35,"area":"alignment"},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2406.19371","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","created":"2024-06-27","cited_by_count":34,"area":"alignment"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2405.17888","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment","created":"2024-05-28","cited_by_count":32,"area":"alignment"},{"id":"2306.00398","title":"Preference-grounded Token-level Guidance for Language Model Fine-tuning","created":"2023-06-01","cited_by_count":31,"area":"alignment"},{"id":"2406.10957","title":"Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence","created":"2024-06-16","cited_by_count":31,"area":"alignment"},{"id":"2307.16851","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","created":"2023-07-31","cited_by_count":30,"area":"alignment"},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2305.18505","title":"Provable Reward-Agnostic Preference-Based Reinforcement Learning","created":"2023-05-29","cited_by_count":25,"area":"alignment"},{"id":"2407.06443","title":"Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment","created":"2024-07-08","cited_by_count":25,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2406.08725","title":"RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs","created":"2024-06-13","cited_by_count":23,"area":"alignment"},{"id":"2310.02368","title":"Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation","created":"2023-10-03","cited_by_count":21,"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":"2406.16897","title":"InstructPatentGPT: Training patent language models to follow instructions with human feedback","created":"2024-05-25","cited_by_count":19,"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":"2403.00199","title":"Improving Socratic Question Generation using Data Augmentation and Preference Optimization","created":"2024-03-01","cited_by_count":16,"area":"alignment"},{"id":"2402.14688","title":"Q-Probe: A Lightweight Approach to Reward Maximization for Language Models","created":"2024-02-22","cited_by_count":15,"area":"alignment"},{"id":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","cited_by_count":15,"area":"alignment"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2406.02756","title":"Aligning Large Language Models via Fine-grained Supervision","created":"2024-06-04","cited_by_count":13,"area":"alignment"},{"id":"2408.14874","title":"Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data","created":"2024-08-27","cited_by_count":12,"area":"alignment"},{"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":"2403.13578","title":"Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation","created":"2024-03-20","cited_by_count":10,"area":"alignment"},{"id":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2307.00279","title":"Let Me Teach You: Pedagogical Foundations of Feedback for Language Models","created":"2023-07-01","cited_by_count":9,"area":"alignment"},{"id":"2402.14228","title":"COPR: Continual Human Preference Learning via Optimal Policy Regularization","created":"2024-02-22","cited_by_count":9,"area":"alignment"},{"id":"2412.16451","title":"Correcting Large Language Model Behavior via Influence Function","created":"2024-12-21","cited_by_count":9,"area":"alignment"},{"id":"2506.10054","title":"Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs","created":"2025-06-11","cited_by_count":9,"area":"alignment"},{"id":"2403.14238","title":"Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection","created":"2024-03-21","cited_by_count":8,"area":"alignment"},{"id":"2407.03856","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","created":"2024-07-04","cited_by_count":7,"area":"alignment"},{"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":"2312.02206","title":"Axiomatic Preference Modeling for Longform Question Answering","created":"2023-12-02","cited_by_count":6,"area":"alignment"},{"id":"2402.14760","title":"Generalizing Reward Modeling for Out-of-Distribution Preference Learning","created":"2024-02-22","cited_by_count":6,"area":"alignment"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2506.07492","title":"Explicit Preference Optimization: No Need for an Implicit Reward Model","created":"2025-06-09","cited_by_count":6,"area":"alignment"},{"id":"2407.01470","title":"DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging","created":"2024-07-01","cited_by_count":5,"area":"alignment"},{"id":"2407.09072","title":"New Desiderata for Direct Preference Optimization","created":"2024-07-12","cited_by_count":5,"area":"alignment"},{"id":"2411.02442","title":"TODO: Enhancing LLM Alignment with Ternary Preferences","created":"2024-11-02","cited_by_count":5,"area":"alignment"},{"id":"2503.03039","title":"LLM Misalignment via Adversarial RLHF Platforms","created":"2025-03-04","cited_by_count":5,"area":"alignment"},{"id":"2312.16430","title":"Preference as Reward, Maximum Preference Optimization with Importance Sampling","created":"2023-12-27","cited_by_count":4,"area":"alignment"},{"id":"2412.20834","title":"Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment","created":"2024-12-30","cited_by_count":4,"area":"alignment"},{"id":"2502.13603","title":"Efficient Safety Retrofitting Against Jailbreaking for LLMs","created":"2025-02-19","cited_by_count":4,"area":"alignment"},{"id":"2503.20995","title":"ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2507.18417","title":"FinDPO: Financial Sentiment Analysis for Algorithmic Trading through Preference Optimization of LLMs","created":"2025-07-24","cited_by_count":4,"area":"alignment"},{"id":"2401.09566","title":"Aligning Large Language Models with Counterfactual DPO","created":"2024-01-17","cited_by_count":3,"area":"alignment"},{"id":"2406.14457","title":"Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue","created":"2024-06-20","cited_by_count":3,"area":"alignment"},{"id":"2310.15694","title":"COPR: Continual Learning Human Preference through Optimal Policy Regularization","created":"2023-10-24","cited_by_count":2,"area":"alignment"},{"id":"2403.04283","title":"Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy","created":"2024-03-07","cited_by_count":2,"area":"alignment"},{"id":"2410.12194","title":"Negative-Prompt-driven Alignment for Generative Language Model","created":"2024-10-16","cited_by_count":2,"area":"alignment"},{"id":"2507.17107","title":"Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models","created":"2025-07-23","cited_by_count":2,"area":"alignment"},{"id":"2503.18347","title":"Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners","created":"2025-03-24","cited_by_count":1,"area":"alignment"},{"id":"2311.00953","title":"Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generation","created":"2023-11-02","cited_by_count":0,"area":"alignment"},{"id":"2405.14103","title":"Online Self-Preferring Language Models","created":"2024-05-23","cited_by_count":0,"area":"alignment"},{"id":"2406.18954","title":"Alignment For Performance Improvement in Conversation Bots","created":"2024-06-27","cited_by_count":0,"area":"alignment"},{"id":"2409.17545","title":"Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult","created":"2024-09-26","cited_by_count":0,"area":"alignment"},{"id":"2409.17791","title":"Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness","created":"2024-09-26","cited_by_count":0,"area":"alignment"},{"id":"2410.10228","title":"QE-EBM: Using Quality Estimators as Energy Loss for Machine Translation","created":"2024-10-14","cited_by_count":0,"area":"alignment"},{"id":"2412.14308","title":"Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation","created":"2024-12-18","cited_by_count":0,"area":"alignment"},{"id":"2601.06108","title":"From RLHF to Direct Alignment: A Theoretical Unification of Preference Learning for Large Language Models","created":"2026-01-03","cited_by_count":0,"area":"alignment"},{"id":"2604.01787","title":"DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment","created":"2026-04-02","cited_by_count":0,"area":"alignment"},{"id":"2606.10528","title":"Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output","created":"2026-06-09","cited_by_count":0,"area":"alignment"},{"id":"2606.30339","title":"REAR: Test-time Preference Realignment through Reward Decomposition","created":"2026-06-29","cited_by_count":0,"area":"alignment"}],"next_cursor":null}