{"total":129,"rows":[{"id":"2402.06782","title":"Debating with More Persuasive LLMs Leads to More Truthful Answers","created":"2024-02-09","cited_by_count":266,"area":"alignment"},{"id":"2411.01111","title":"Rule Based Rewards for Language Model Safety","created":"2024-11-02","cited_by_count":108,"area":"alignment"},{"id":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"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":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"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":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46,"area":"alignment"},{"id":"2407.00617","title":"Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning","created":"2024-06-30","cited_by_count":45,"area":"alignment"},{"id":"2508.03686","title":"CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward","created":"2025-08-05","cited_by_count":40,"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":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2409.15268","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking","created":"2024-09-23","cited_by_count":35,"area":"alignment"},{"id":"2506.19248","title":"Inference-Time Reward Hacking in Large Language Models","created":"2025-06-24","cited_by_count":34,"area":"alignment"},{"id":"2409.11239","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","created":"2024-09-17","cited_by_count":32,"area":"alignment"},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"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":"2502.16852","title":"Improving LLM General Preference Alignment via Optimistic Online Mirror Descent","created":"2025-02-24","cited_by_count":24,"area":"alignment"},{"id":"2412.06000","title":"Does RLHF Scale? Exploring the Impacts From Data, Model, and Method","created":"2024-12-08","cited_by_count":23,"area":"alignment"},{"id":"2602.01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","created":"2026-02-02","cited_by_count":21,"area":"alignment"},{"id":"2501.12273","title":"Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement","created":"2025-01-21","cited_by_count":18,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2507.21183","title":"MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge","created":"2025-07-27","cited_by_count":15,"area":"alignment"},{"id":"2607.15161","title":"On-Policy Delta Distillation","created":"2026-07-16","cited_by_count":15,"area":"alignment"},{"id":"2409.02231","title":"SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration","created":"2024-09-03","cited_by_count":14,"area":"alignment"},{"id":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","cited_by_count":14,"area":"alignment"},{"id":"2510.01555","title":"Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization","created":"2025-10-02","cited_by_count":14,"area":"alignment"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2505.10527","title":"WorldPM: Scaling Human Preference Modeling","created":"2025-05-15","cited_by_count":13,"area":"alignment"},{"id":"2605.07396","title":"Rubric-based On-policy Distillation","created":"2026-05-08","cited_by_count":13,"area":"alignment"},{"id":"2412.01253","title":"Yi-Lightning Technical Report","created":"2024-12-02","cited_by_count":12,"area":"alignment"},{"id":"2505.21605","title":"SoSBench: Benchmarking Safety Alignment on Six Scientific Domains","created":"2025-05-27","cited_by_count":12,"area":"alignment"},{"id":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","cited_by_count":10,"area":"alignment"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2505.11166","title":"SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization","created":"2025-05-16","cited_by_count":10,"area":"alignment"},{"id":"2510.17426","title":"Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging","created":"2025-10-20","cited_by_count":10,"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":"2604.02795","title":"Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks","created":"2026-04-03","cited_by_count":10,"area":"alignment"},{"id":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9,"area":"alignment"},{"id":"2502.00666","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","created":"2025-02-02","cited_by_count":8,"area":"alignment"},{"id":"2512.23457","title":"Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following","created":"2025-12-29","cited_by_count":8,"area":"alignment"},{"id":"2509.23102","title":"Multiplayer Nash Preference Optimization","created":"2025-09-27","cited_by_count":7,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2503.04222","title":"FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion","created":"2025-03-06","cited_by_count":6,"area":"alignment"},{"id":"2601.10589","title":"Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay","created":"2026-01-15","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":"2602.07892","title":"Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection","created":"2026-02-08","cited_by_count":6,"area":"alignment"},{"id":"2603.01907","title":"Efficient RLVR Training via Weighted Mutual Information Data Selection","created":"2026-03-02","cited_by_count":6,"area":"alignment"},{"id":"2502.03397","title":"SPRI: Aligning Large Language Models with Context-Situated Principles","created":"2025-02-05","cited_by_count":5,"area":"alignment"},{"id":"2509.22099","title":"S2J: Bridging the Gap Between Solving and Judging Ability in Generative Reward Models","created":"2025-09-26","cited_by_count":5,"area":"alignment"},{"id":"2604.04215","title":"DARE: Diffusion Large Language Models Alignment and Reinforcement Executor","created":"2026-04-05","cited_by_count":5,"area":"alignment"},{"id":"2406.19071","title":"EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization","created":"2024-06-27","cited_by_count":4,"area":"alignment"},{"id":"2502.04675","title":"Scalable Oversight for Superhuman AI via Recursive Self-Critiquing","created":"2025-02-07","cited_by_count":4,"area":"alignment"},{"id":"2505.03059","title":"Improving Model Alignment Through Collective Intelligence of Open-Source LLMS","created":"2025-05-05","cited_by_count":4,"area":"alignment"},{"id":"2605.26579","title":"Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards","created":"2026-05-26","cited_by_count":4,"area":"alignment"},{"id":"2606.03361","title":"Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning","created":"2026-06-02","cited_by_count":4,"area":"alignment"},{"id":"2606.24014","title":"Reinforcement Learning Towards Broadly and Persistently Beneficial Models","created":"2026-06-22","cited_by_count":4,"area":"alignment"},{"id":"2510.17923","title":"Rewarding the Journey, Not Just the Destination: A Composite Path and Answer Self-Scoring Reward Mechanism for Test-Time Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":"alignment"},{"id":"2510.18081","title":"Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth","created":"2025-10-20","cited_by_count":3,"area":"alignment"},{"id":"2601.22801","title":"Clipping-Free Policy Optimization for Large Language Models","created":"2026-01-30","cited_by_count":3,"area":"alignment"},{"id":"2602.06763","title":"R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2604.17501","title":"CoAct: Co-Active LLM Preference Learning with Human-AI Synergy","created":"2026-04-19","cited_by_count":3,"area":"alignment"},{"id":"2605.05750","title":"RVPO: Risk-Sensitive Alignment via Variance Regularization","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2505.18799","title":"ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models","created":"2025-05-24","cited_by_count":2,"area":"alignment"},{"id":"2508.08243","title":"Jinx: Unlimited LLMs for Probing Alignment Failures","created":"2025-08-11","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":"2509.13079","title":"When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning","created":"2025-09-16","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":"2602.13551","title":"Small Reward Models via Backward Inference","created":"2026-02-14","cited_by_count":2,"area":"alignment"},{"id":"2602.22718","title":"RLHFless: Serverless Computing for Efficient RLHF","created":"2026-02-26","cited_by_count":2,"area":"alignment"},{"id":"2603.08104","title":"Invisible Safety Threat: Malicious Finetuning for LLM via Steganography","created":"2026-03-09","cited_by_count":2,"area":"alignment"},{"id":"2604.02174","title":"Quantifying Self-Preservation Bias in Large Language Models","created":"2026-04-02","cited_by_count":2,"area":"alignment"},{"id":"2606.21906","title":"Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding","created":"2026-06-20","cited_by_count":2,"area":"alignment"},{"id":"2607.03528","title":"Aligning Language Models with Selective Prediction","created":"2026-07-03","cited_by_count":2,"area":"alignment"},{"id":"2608.09123","title":"RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning","created":"2026-08-10","cited_by_count":2,"area":"alignment"},{"id":"2608.19982","title":"COPA: Continual Preference Optimization for Adaptive Prompt Injection Defense","created":"2026-08-20","cited_by_count":2,"area":"alignment"},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2504.06562","title":"FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion","created":"2025-04-09","cited_by_count":1,"area":"alignment"},{"id":"2508.09463","title":"User-centric Subjective Leaderboard by Customizable Reward Modeling","created":"2025-08-13","cited_by_count":1,"area":"alignment"},{"id":"2508.10031","title":"Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs","created":"2025-08-09","cited_by_count":1,"area":"alignment"},{"id":"2509.25148","title":"AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"id":"2510.05526","title":"Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2510.20187","title":"Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values","created":"2025-10-23","cited_by_count":1,"area":"alignment"},{"id":"2510.21090","title":"Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only","created":"2025-10-24","cited_by_count":1,"area":"alignment"},{"id":"2511.10985","title":"When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets","created":"2025-11-14","cited_by_count":1,"area":"alignment"},{"id":"2512.05464","title":"Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment","created":"2025-12-05","cited_by_count":1,"area":"alignment"},{"id":"2603.01375","title":"Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation","created":"2026-03-02","cited_by_count":1,"area":"alignment"},{"id":"2605.01899","title":"Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment","created":"2026-05-03","cited_by_count":1,"area":"alignment"},{"id":"2605.15464","title":"GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero","created":"2026-05-14","cited_by_count":1,"area":"alignment"},{"id":"2605.29275","title":"Prompt-Level Reward Specifications for Open-Ended Post-Training","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2605.29582","title":"PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2606.00357","title":"From \"Weak\" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging","created":"2026-05-29","cited_by_count":1,"area":"alignment"},{"id":"2606.25442","title":"PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models","created":"2026-06-24","cited_by_count":1,"area":"alignment"},{"id":"2607.29246","title":"Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2608.24231","title":"RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges","created":"2026-08-25","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":"2505.10775","title":"A Systematic Analysis of Base Model Choice for Reward Modeling","created":"2025-05-16","cited_by_count":0,"area":"alignment"},{"id":"2506.02018","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","created":"2025-05-28","cited_by_count":0,"area":"alignment"},{"id":"2510.15746","title":"LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation","created":"2025-10-17","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}