{"total":127,"rows":[{"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":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2309.07124","title":"RAIN: Your Language Models Can Align Themselves without Finetuning","created":"2023-09-13","cited_by_count":157,"area":"alignment"},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2410.03642","title":"Aligning LLMs with Individual Preferences via Interaction","created":"2024-10-04","cited_by_count":63,"area":"alignment"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2603.02115","title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","created":"2026-03-02","cited_by_count":60,"area":"alignment"},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57,"area":"alignment"},{"id":"2406.08469","title":"PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences","created":"2024-06-12","cited_by_count":54,"area":"alignment"},{"id":"2410.06961","title":"Self-Boosting Large Language Models with Synthetic Preference Data","created":"2024-10-09","cited_by_count":40,"area":"alignment"},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2410.10624","title":"SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition","created":"2024-10-14","cited_by_count":38,"area":"alignment"},{"id":"2305.01918","title":"Improving Contrastive Learning of Sentence Embeddings from AI Feedback","created":"2023-05-03","cited_by_count":29,"area":"alignment"},{"id":"2406.05587","title":"Creativity Has Left the Chat: The Price of Debiasing Language Models","created":"2024-06-08","cited_by_count":29,"area":"alignment"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2410.19133","title":"Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback","created":"2024-10-24","cited_by_count":26,"area":"alignment"},{"id":"2401.11458","title":"Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback","created":"2024-01-21","cited_by_count":25,"area":"alignment"},{"id":"2404.01054","title":"Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment","created":"2024-04-01","cited_by_count":25,"area":"alignment"},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25,"area":"alignment"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"area":"alignment"},{"id":"2507.05129","title":"SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Prediction","created":"2025-07-07","cited_by_count":23,"area":"alignment"},{"id":"2512.24551","title":"PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation","created":"2025-12-31","cited_by_count":23,"area":"alignment"},{"id":"2407.07342","title":"Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture","created":"2024-07-10","cited_by_count":22,"area":"alignment"},{"id":"2506.02095","title":"Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences","created":"2025-06-02","cited_by_count":22,"area":"alignment"},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"id":"2210.15893","title":"When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labels","created":"2022-10-28","cited_by_count":20,"area":"alignment"},{"id":"2403.01304","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","created":"2024-03-02","cited_by_count":20,"area":"alignment"},{"id":"2406.10522","title":"Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning","created":"2024-06-15","cited_by_count":19,"area":"alignment"},{"id":"2507.05619","title":"Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests","created":"2025-07-08","cited_by_count":19,"area":"alignment"},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18,"area":"alignment"},{"id":"2410.03145","title":"Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback","created":"2024-10-04","cited_by_count":15,"area":"alignment"},{"id":"2501.11463","title":"Curiosity-Driven Reinforcement Learning from Human Feedback","created":"2025-01-20","cited_by_count":15,"area":"alignment"},{"id":"2503.01048","title":"Personalize Your LLM: Fake it then Align it","created":"2025-03-02","cited_by_count":15,"area":"alignment"},{"id":"2504.16438","title":"POPri: Private Federated Learning using Preference-Optimized Synthetic Data","created":"2025-04-23","cited_by_count":14,"area":"alignment"},{"id":"2606.23038","title":"EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement Learning","created":"2026-06-22","cited_by_count":14,"area":"alignment"},{"id":"2204.05512","title":"Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback","created":"2022-04-12","cited_by_count":13,"area":"alignment"},{"id":"2406.10977","title":"Toward Optimal LLM Alignments Using Two-Player Games","created":"2024-06-16","cited_by_count":13,"area":"alignment"},{"id":"2411.08733","title":"Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models","created":"2024-11-13","cited_by_count":13,"area":"alignment"},{"id":"2507.21182","title":"SDD: Self-Degraded Defense against Malicious Fine-tuning","created":"2025-07-27","cited_by_count":13,"area":"alignment"},{"id":"2509.19333","title":"Pluralistic Off-policy Evaluation and Alignment","created":"2025-09-15","cited_by_count":11,"area":"alignment"},{"id":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2411.16502","title":"Interpreting Language Reward Models via Contrastive Explanations","created":"2024-11-25","cited_by_count":9,"area":"alignment"},{"id":"2502.19158","title":"When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning","created":"2025-02-26","cited_by_count":9,"area":"alignment"},{"id":"2402.09872","title":"Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community","created":"2024-02-15","cited_by_count":8,"area":"alignment"},{"id":"2210.15906","title":"Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences","created":"2022-10-28","cited_by_count":7,"area":"alignment"},{"id":"2310.15758","title":"Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?","created":"2023-10-24","cited_by_count":7,"area":"alignment"},{"id":"2407.17112","title":"Neural Dueling Bandits: Preference-Based Optimization with Human Feedback","created":"2024-07-24","cited_by_count":7,"area":"alignment"},{"id":"2410.11370","title":"Enhance Graph Alignment for Large Language Models","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2402.09320","title":"ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization","created":"2024-02-14","cited_by_count":6,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2410.15096","title":"GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2505.23473","title":"EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions","created":"2025-05-29","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":"2601.18292","title":"TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment","created":"2026-01-26","cited_by_count":6,"area":"alignment"},{"id":"2601.18533","title":"From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation","created":"2026-01-26","cited_by_count":6,"area":"alignment"},{"id":"2603.20957","title":"Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models","created":"2026-03-21","cited_by_count":6,"area":"alignment"},{"id":"2412.19396","title":"Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe","created":"2024-12-27","cited_by_count":5,"area":"alignment"},{"id":"2511.00689","title":"Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?","created":"2025-11-01","cited_by_count":5,"area":"alignment"},{"id":"2406.08842","title":"ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions","created":"2024-06-13","cited_by_count":4,"area":"alignment"},{"id":"2406.11581","title":"Style Transfer with Multi-iteration Preference Optimization","created":"2024-06-17","cited_by_count":4,"area":"alignment"},{"id":"2509.13244","title":"Evaluating LLM Alignment on Personality Inference from Real-World Interview Data","created":"2025-09-16","cited_by_count":4,"area":"alignment"},{"id":"2602.07639","title":"Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization","created":"2026-02-07","cited_by_count":4,"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":"2407.12847","title":"Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessments","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2507.18802","title":"DxHF: Providing High-Quality Human Feedback for LLM Alignment via Interactive Decomposition","created":"2025-07-24","cited_by_count":3,"area":"alignment"},{"id":"2604.18943","title":"Personalized Benchmarking: Evaluating LLMs by Individual Preferences","created":"2026-04-21","cited_by_count":3,"area":"alignment"},{"id":"2402.18284","title":"Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization","created":"2024-02-28","cited_by_count":2,"area":"alignment"},{"id":"2406.06587","title":"TouchAI: Exploring human-AI perceptual alignment in touch through language model representations","created":"2024-06-05","cited_by_count":2,"area":"alignment"},{"id":"2503.17965","title":"Understanding the Effects of RLHF on the Quality and Detectability of LLM-Generated Texts","created":"2025-03-23","cited_by_count":2,"area":"alignment"},{"id":"2601.05882","title":"An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift","created":"2026-01-09","cited_by_count":2,"area":"alignment"},{"id":"2603.12795","title":"SteerRM: Debiasing Reward Models via Sparse Autoencoders","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2603.16978","title":"Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models","created":"2026-03-17","cited_by_count":2,"area":"alignment"},{"id":"2605.02647","title":"ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming","created":"2026-05-04","cited_by_count":2,"area":"alignment"},{"id":"2605.30273","title":"LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community Feedback","created":"2026-05-28","cited_by_count":2,"area":"alignment"},{"id":"2606.01196","title":"Low-Resource Safety Failures Are Action Failures, Not Representation Failures","created":"2026-05-31","cited_by_count":2,"area":"alignment"},{"id":"2405.09747","title":"NIFTY Financial News Headlines Dataset","created":"2024-05-16","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":"2505.12322","title":"Model alignment using inter-modal bridges","created":"2025-05-18","cited_by_count":1,"area":"alignment"},{"id":"2506.04464","title":"Leveraging Reward Models for Guiding Code Review Comment Generation","created":"2025-06-04","cited_by_count":1,"area":"alignment"},{"id":"2510.07557","title":"Investigating Thematic Patterns and User Preferences in LLM Interactions using BERTopic","created":"2025-10-08","cited_by_count":1,"area":"alignment"},{"id":"2510.14459","title":"Holdout-Loss-Based Data Selection for LLM Finetuning via In-Context Learning","created":"2025-10-16","cited_by_count":1,"area":"alignment"},{"id":"2511.23184","title":"Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction","created":"2025-11-28","cited_by_count":1,"area":"alignment"},{"id":"2512.03704","title":"Overcoming State Inertia: Minimally Invasive Temporal Alignment for Evolving Contexts","created":"2025-12-03","cited_by_count":1,"area":"alignment"},{"id":"2601.05075","title":"SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment","created":"2026-01-08","cited_by_count":1,"area":"alignment"},{"id":"2601.08097","title":"AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling","created":"2026-01-13","cited_by_count":1,"area":"alignment"},{"id":"2601.12758","title":"VISPA: Pluralistic Alignment via Automatic Value Selection and Activation","created":"2026-01-19","cited_by_count":1,"area":"alignment"},{"id":"2603.29123","title":"Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2604.00200","title":"Offline Constrained RLHF with Multiple Preference Oracles","created":"2026-03-31","cited_by_count":1,"area":"alignment"},{"id":"2604.03238","title":"RLHF May Not Reflect Genuine Preferences","created":"2026-01-31","cited_by_count":1,"area":"alignment"},{"id":"2604.16659","title":"Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs","created":"2026-04-17","cited_by_count":1,"area":"alignment"},{"id":"2604.17769","title":"Reverse Constitutional AI: A Framework for Controllable Toxic Data Generation via Probability-Clamped RLAIF","created":"2026-04-20","cited_by_count":1,"area":"alignment"},{"id":"2605.28802","title":"Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization","created":"2026-05-27","cited_by_count":1,"area":"alignment"},{"id":"2606.00291","title":"The Representation-Rationalizability Tradeoff in Reward Learning","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2609.14896","title":"Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning","created":"2026-09-14","cited_by_count":1,"area":"alignment"},{"id":"2406.01070","title":"Guiding ChatGPT to Generate Salient Domain Summaries","created":"2024-06-03","cited_by_count":0,"area":"alignment"},{"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":"2408.02861","title":"A Framework for Fine-Tuning LLMs using Heterogeneous Feedback","created":"2024-08-05","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"}],"next_cursor":"100"}