{"total":104,"rows":[{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588,"area":"alignment"},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150,"area":"alignment"},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057,"area":"alignment"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302,"area":"alignment"},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2302.02676","title":"Chain of Hindsight Aligns Language Models with Feedback","created":"2023-02-06","cited_by_count":148,"area":"alignment"},{"id":"2404.18922","title":"DPO Meets PPO: Reinforced Token Optimization for RLHF","created":"2024-04-29","cited_by_count":127,"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":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120,"area":"alignment"},{"id":"2203.10050","title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","created":"2022-03-18","cited_by_count":97,"area":"alignment"},{"id":"2402.16192","title":"Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing","created":"2024-02-25","cited_by_count":74,"area":"alignment"},{"id":"1707.07402","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","created":"2017-07-24","cited_by_count":72,"area":"alignment"},{"id":"2402.10500","title":"Active Preference Optimization for Sample Efficient RLHF","created":"2024-02-16","cited_by_count":62,"area":"alignment"},{"id":"2205.12401","title":"Reward Uncertainty for Exploration in Preference-based Reinforcement Learning","created":"2022-05-24","cited_by_count":61,"area":"alignment"},{"id":"1805.10627","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","created":"2018-05-27","cited_by_count":57,"area":"alignment"},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"1902.04257","title":"Deep Reinforcement Learning from Policy-Dependent Human Feedback","created":"2019-02-12","cited_by_count":56,"area":"alignment"},{"id":"2009.13649","title":"The EMPATHIC Framework for Task Learning from Implicit Human Feedback","created":"2020-09-28","cited_by_count":38,"area":"alignment"},{"id":"2504.14439","title":"LoRe: Personalizing LLMs via Low-Rank Reward Modeling","created":"2025-04-20","cited_by_count":38,"area":"alignment"},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37,"area":"alignment"},{"id":"2401.05675","title":"Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation","created":"2024-01-11","cited_by_count":36,"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":"2503.15463","title":"From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment","created":"2025-03-19","cited_by_count":30,"area":"alignment"},{"id":"2405.17931","title":"Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment","created":"2024-05-28","cited_by_count":28,"area":"alignment"},{"id":"2211.11602","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","created":"2022-11-21","cited_by_count":26,"area":"alignment"},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"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":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23,"area":"alignment"},{"id":"2406.11817","title":"Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level","created":"2024-06-17","cited_by_count":22,"area":"alignment"},{"id":"2412.05210","title":"Evaluating and Aligning CodeLLMs on Human Preference","created":"2024-12-06","cited_by_count":22,"area":"alignment"},{"id":"1708.02300","title":"Reinforced Video Captioning with Entailment Rewards","created":"2017-08-07","cited_by_count":21,"area":"alignment"},{"id":"2301.03652","title":"On The Fragility of Learned Reward Functions","created":"2023-01-09","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":"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":"2311.09132","title":"Aligning Neural Machine Translation Models: Human Feedback in Training and Inference","created":"2023-11-15","cited_by_count":19,"area":"alignment"},{"id":"2410.21662","title":"$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization","created":"2024-10-29","cited_by_count":19,"area":"alignment"},{"id":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2508.08746","title":"Interpretable Reward Model via Sparse Autoencoder","created":"2025-08-12","cited_by_count":18,"area":"alignment"},{"id":"2302.00270","title":"Internally Rewarded Reinforcement Learning","created":"2023-02-01","cited_by_count":14,"area":"alignment"},{"id":"2308.12050","title":"Aligning Language Models with Offline Learning from Human Feedback","created":"2023-08-23","cited_by_count":14,"area":"alignment"},{"id":"2310.03013","title":"SemiReward: A General Reward Model for Semi-supervised Learning","created":"2023-10-04","cited_by_count":14,"area":"alignment"},{"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":"2503.05079","title":"On a Connection Between Imitation Learning and RLHF","created":"2025-03-07","cited_by_count":13,"area":"alignment"},{"id":"2506.03690","title":"Robust Preference Optimization via Dynamic Target Margins","created":"2025-06-04","cited_by_count":13,"area":"alignment"},{"id":"2106.04316","title":"Exploration and preference satisfaction trade-off in reward-free learning","created":"2021-06-08","cited_by_count":12,"area":"alignment"},{"id":"2412.15538","title":"FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF","created":"2024-12-20","cited_by_count":12,"area":"alignment"},{"id":"2502.07340","title":"Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering","created":"2025-02-11","cited_by_count":12,"area":"alignment"},{"id":"2208.14165","title":"Towards Boosting the Open-Domain Chatbot with Human Feedback","created":"2022-08-30","cited_by_count":11,"area":"alignment"},{"id":"2408.11481","title":"VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment","created":"2024-08-21","cited_by_count":11,"area":"alignment"},{"id":"2411.05986","title":"Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings","created":"2024-11-08","cited_by_count":11,"area":"alignment"},{"id":"2009.12600","title":"Online Learning of Non-Markovian Reward Models","created":"2020-09-26","cited_by_count":9,"area":"alignment"},{"id":"2410.05102","title":"SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks","created":"2024-10-07","cited_by_count":9,"area":"alignment"},{"id":"2406.16743","title":"Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions","created":"2024-06-24","cited_by_count":8,"area":"alignment"},{"id":"2410.07779","title":"Modeling User Preferences with Automatic Metrics: Creating a High-Quality Preference Dataset for Machine Translation","created":"2024-10-10","cited_by_count":8,"area":"alignment"},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2406.16783","title":"M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2410.04346","title":"Permutative Preference Alignment from Listwise Ranking of Human Judgments","created":"2024-10-06","cited_by_count":7,"area":"alignment"},{"id":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2504.10208","title":"From Prompting to Alignment: A Generative Framework for Query Recommendation","created":"2025-04-14","cited_by_count":7,"area":"alignment"},{"id":"2505.08507","title":"InfoPO: On Mutual Information Maximization for Large Language Model Alignment","created":"2025-05-13","cited_by_count":7,"area":"alignment"},{"id":"2505.20081","title":"Inference-time Alignment in Continuous Space","created":"2025-05-26","cited_by_count":7,"area":"alignment"},{"id":"2508.17229","title":"Multi-Metric Preference Alignment for Generative Speech Restoration","created":"2025-08-24","cited_by_count":7,"area":"alignment"},{"id":"2412.06827","title":"Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback","created":"2024-12-06","cited_by_count":6,"area":"alignment"},{"id":"2503.14391","title":"How much do LLMs learn from negative examples?","created":"2025-03-18","cited_by_count":6,"area":"alignment"},{"id":"2506.17353","title":"Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs","created":"2025-06-20","cited_by_count":6,"area":"alignment"},{"id":"2201.08102","title":"Safe Deep RL in 3D Environments using Human Feedback","created":"2022-01-20","cited_by_count":5,"area":"alignment"},{"id":"2406.07971","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2501.07886","title":"Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision","created":"2025-01-14","cited_by_count":5,"area":"alignment"},{"id":"2504.11337","title":"REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective","created":"2025-04-15","cited_by_count":5,"area":"alignment"},{"id":"2211.06527","title":"Rewards Encoding Environment Dynamics Improves Preference-based Reinforcement Learning","created":"2022-11-12","cited_by_count":4,"area":"alignment"},{"id":"2306.13588","title":"System-Level Natural Language Feedback","created":"2023-06-23","cited_by_count":4,"area":"alignment"},{"id":"2503.15880","title":"InCo-DPO: Balancing Distribution Shift and Data Quality for Enhanced Preference Optimization","created":"2025-03-20","cited_by_count":4,"area":"alignment"},{"id":"2404.10306","title":"Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models","created":"2024-04-16","cited_by_count":3,"area":"alignment"},{"id":"2410.05782","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","created":"2024-10-08","cited_by_count":3,"area":"alignment"},{"id":"2502.01237","title":"The Differences Between Direct Alignment Algorithms are a Blur","created":"2025-02-03","cited_by_count":3,"area":"alignment"},{"id":"2503.16929","title":"TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment","created":"2025-03-21","cited_by_count":3,"area":"alignment"},{"id":"2504.10002","title":"FLoRA: Sample-Efficient Preference-based RL via Low-Rank Style Adaptation of Reward Functions","created":"2025-04-14","cited_by_count":3,"area":"alignment"},{"id":"2510.15839","title":"Learning Correlated Reward Models: Statistical Barriers and Opportunities","created":"2025-10-17","cited_by_count":3,"area":"alignment"},{"id":"2601.12535","title":"Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning","created":"2026-01-18","cited_by_count":3,"area":"alignment"},{"id":"2607.21356","title":"Emergent Misalignment Recruits a Pre-existing Persona Subspace","created":"2026-07-23","cited_by_count":3,"area":"alignment"},{"id":"2505.08849","title":"Improved Algorithms for Differentially Private Language Model Alignment","created":"2025-05-13","cited_by_count":2,"area":"alignment"},{"id":"2508.14853","title":"Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent","created":"2025-08-20","cited_by_count":2,"area":"alignment"},{"id":"2509.01938","title":"EigenBench: A Comparative Behavioral Measure of Value Alignment","created":"2025-09-02","cited_by_count":2,"area":"alignment"},{"id":"2509.10515","title":"Adaptive Preference Optimization with Uncertainty-aware Utility Anchor","created":"2025-09-03","cited_by_count":2,"area":"alignment"},{"id":"2511.09385","title":"AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment","created":"2025-11-12","cited_by_count":2,"area":"alignment"},{"id":"1909.03622","title":"Transfer Reward Learning for Policy Gradient-Based Text Generation","created":"2019-09-09","cited_by_count":1,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2412.10529","title":"Solving the Inverse Alignment Problem for Efficient RLHF","created":"2024-12-13","cited_by_count":1,"area":"alignment"},{"id":"2503.01233","title":"PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy Extrapolation","created":"2025-03-03","cited_by_count":1,"area":"alignment"},{"id":"2510.19562","title":"DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2606.28249","title":"HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2305.16924","title":"Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback","created":"2023-05-26","cited_by_count":0,"area":"alignment"},{"id":"2408.16827","title":"Fluent and Accurate Image Captioning with a Self-Trained Reward Model","created":"2024-08-29","cited_by_count":0,"area":"alignment"},{"id":"2410.06118","title":"Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learning","created":"2024-10-08","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":"2506.11098","title":"Debiasing Online Preference Learning via Preference Feature Preservation","created":"2025-06-06","cited_by_count":0,"area":"alignment"},{"id":"2509.24781","title":"SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models","created":"2025-09-29","cited_by_count":0,"area":"alignment"},{"id":"2512.10601","title":"Multi-Objective Reward and Preference Optimization: Theory and Algorithms","created":"2025-12-11","cited_by_count":0,"area":"alignment"},{"id":"2602.18582","title":"Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications","created":"2026-02-20","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}