{"total":83,"rows":[{"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":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","cited_by_count":21,"area":"alignment"},{"id":"2601.03444","title":"Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale","created":"2026-01-06","cited_by_count":20,"area":"alignment"},{"id":"2505.22338","title":"Text2Grad: Reinforcement Learning from Natural Language Feedback","created":"2025-05-28","cited_by_count":18,"area":"alignment"},{"id":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17,"area":"alignment"},{"id":"2605.09959","title":"G-Zero: Self-Play for Open-Ended Generation from Zero Data","created":"2026-05-11","cited_by_count":17,"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":"2506.15068","title":"Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation","created":"2025-06-18","cited_by_count":11,"area":"alignment"},{"id":"2507.07375","title":"Bradley-Terry and Multi-Objective Reward Modeling Are Complementary","created":"2025-07-10","cited_by_count":11,"area":"alignment"},{"id":"2507.13383","title":"Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models","created":"2025-07-15","cited_by_count":11,"area":"alignment"},{"id":"2509.25361","title":"Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling","created":"2025-09-29","cited_by_count":11,"area":"alignment"},{"id":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10,"area":"alignment"},{"id":"2604.22891","title":"Quantifying and Mitigating Self-Preference Bias of LLM Judges","created":"2026-04-24","cited_by_count":10,"area":"alignment"},{"id":"2504.03612","title":"AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset","created":"2025-04-04","cited_by_count":9,"area":"alignment"},{"id":"2603.08091","title":"Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization","created":"2026-03-09","cited_by_count":9,"area":"alignment"},{"id":"2506.11702","title":"Configurable Preference Tuning with Rubric-Guided Synthetic Data","created":"2025-06-13","cited_by_count":8,"area":"alignment"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"id":"2502.10563","title":"Accelerating Unbiased LLM Evaluation via Synthetic Feedback","created":"2025-02-14","cited_by_count":7,"area":"alignment"},{"id":"2510.04320","title":"Read the Scene, Not the Script: Outcome-Aware Safety for LLMs","created":"2025-10-05","cited_by_count":6,"area":"alignment"},{"id":"2507.02332","title":"PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage","created":"2025-07-03","cited_by_count":5,"area":"alignment"},{"id":"2508.12935","title":"Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards","created":"2025-08-18","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":"2602.03876","title":"GOPO: Policy Optimization using Ranked Rewards","created":"2026-02-01","cited_by_count":5,"area":"alignment"},{"id":"2603.00610","title":"CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction","created":"2026-02-28","cited_by_count":5,"area":"alignment"},{"id":"2505.13862","title":"PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2508.19922","title":"HEAL: A Hypothesis-Based Preference-Aware Analysis Framework","created":"2025-08-27","cited_by_count":4,"area":"alignment"},{"id":"2510.08048","title":"TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance","created":"2025-10-09","cited_by_count":4,"area":"alignment"},{"id":"2602.09411","title":"K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge","created":"2026-02-10","cited_by_count":4,"area":"alignment"},{"id":"2602.11157","title":"Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety","created":"2025-12-08","cited_by_count":4,"area":"alignment"},{"id":"2602.12116","title":"P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling","created":"2026-02-12","cited_by_count":4,"area":"alignment"},{"id":"2604.02507","title":"Reinforcement Learning from Human Feedback: A Statistical Perspective","created":"2026-04-02","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":"2606.09076","title":"Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions","created":"2026-06-08","cited_by_count":4,"area":"alignment"},{"id":"2505.21907","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","created":"2025-05-28","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":"2508.16921","title":"Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2509.03647","title":"Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators","created":"2025-09-03","cited_by_count":3,"area":"alignment"},{"id":"2602.03160","title":"VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models","created":"2026-02-03","cited_by_count":3,"area":"alignment"},{"id":"2602.20670","title":"CAMEL: Confidence-Gated Reflection for Reward Modeling","created":"2026-02-24","cited_by_count":3,"area":"alignment"},{"id":"2604.13717","title":"On Cost-Effective LLM-as-a-Judge Improvement Techniques","created":"2026-04-15","cited_by_count":3,"area":"alignment"},{"id":"2605.06036","title":"Optimal Transport for LLM Reward Modeling from Noisy Preference","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2608.27505","title":"A Survey on Rubric-Guided Reinforcement Learning for Language Models","created":"2026-08-27","cited_by_count":3,"area":"alignment"},{"id":"2509.03809","title":"Align-then-Slide: A complete evaluation framework for Ultra-Long Document-Level Machine Translation","created":"2025-09-04","cited_by_count":2,"area":"alignment"},{"id":"2510.20498","title":"Robust Preference Alignment via Directional Neighborhood Consensus","created":"2025-10-23","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":"2603.15061","title":"Writer-R1: Enhancing Generative Writing in LLMs via Memory-augmented Replay Policy Optimization","created":"2026-03-16","cited_by_count":2,"area":"alignment"},{"id":"2605.31545","title":"Preference-Aware Rubric Learning for Personalized Evaluation","created":"2026-05-29","cited_by_count":2,"area":"alignment"},{"id":"2506.13702","title":"Value-Free Policy Optimization via Reward Partitioning","created":"2025-06-16","cited_by_count":1,"area":"alignment"},{"id":"2507.17477","title":"An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models","created":"2025-07-23","cited_by_count":1,"area":"alignment"},{"id":"2510.09260","title":"GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis","created":"2025-10-10","cited_by_count":1,"area":"alignment"},{"id":"2510.19967","title":"LyriCAR: A Difficulty-Aware Curriculum Reinforcement Learning Framework For Controllable Lyric Translation","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2601.22513","title":"Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models","created":"2026-01-30","cited_by_count":1,"area":"alignment"},{"id":"2602.01068","title":"From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization","created":"2026-02-01","cited_by_count":1,"area":"alignment"},{"id":"2603.13359","title":"From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions","created":"2026-03-09","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":"2604.04261","title":"APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs","created":"2026-04-05","cited_by_count":1,"area":"alignment"},{"id":"2604.14920","title":"Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models","created":"2026-04-16","cited_by_count":1,"area":"alignment"},{"id":"2605.18721","title":"General Preference Reinforcement Learning","created":"2026-05-18","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":"2606.21089","title":"Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2606.28294","title":"Democratic ICAI: Debating Our Way to Steering Principles from Preferences","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2507.15281","title":"A Novel Self-Evolution Framework for Large Language Models","created":"2025-07-21","cited_by_count":0,"area":"alignment"},{"id":"2508.09937","title":"A Comprehensive Evaluation framework of Alignment Techniques for LLMs","created":"2025-08-13","cited_by_count":0,"area":"alignment"},{"id":"2511.06682","title":"Textual Self-attention Network: Test-Time Preference Optimization through Textual Gradient-based Attention","created":"2025-11-10","cited_by_count":0,"area":"alignment"},{"id":"2511.13007","title":"GEM: Generative Entropy-Guided Preference Modeling for Few-shot Alignment of LLMs","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2603.01784","title":"Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution","created":"2026-03-02","cited_by_count":0,"area":"alignment"},{"id":"2603.21359","title":"Benchmarking Bengali Dialectal Bias: A Multi-Stage Framework Integrating RAG-Based Translation and Human-Augmented RLAIF","created":"2026-03-22","cited_by_count":0,"area":"alignment"},{"id":"2603.25145","title":"Learning to Rank Caption Chains for Video-Text Alignment","created":"2026-03-26","cited_by_count":0,"area":"alignment"},{"id":"2603.28197","title":"EpiPersona: Persona Projection and Episode Coupling for Pluralistic Preference Modeling","created":"2026-03-30","cited_by_count":0,"area":"alignment"},{"id":"2605.11483","title":"StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models","created":"2026-05-12","cited_by_count":0,"area":"alignment"},{"id":"2605.19665","title":"CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging","created":"2026-05-19","cited_by_count":0,"area":"alignment"},{"id":"2605.20994","title":"Towards Context-Invariant Safety Alignment for Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2605.28313","title":"Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2606.24004","title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","created":"2026-06-22","cited_by_count":0,"area":"alignment"},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2608.01629","title":"Human-LLM Alignment in Language Attitudes Toward Non-Native Japanese","created":"2026-08-03","cited_by_count":0,"area":"alignment"},{"id":"2608.21376","title":"On the Role of Citations in Preference Data","created":"2026-07-06","cited_by_count":0,"area":"alignment"},{"id":"2609.06289","title":"Steering Geometry: Validating Human Value Geometry in LLM Steering Space","created":"2026-09-05","cited_by_count":0,"area":"alignment"},{"id":"2609.33803","title":"Diffusion Reward Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.36748","title":"Generalizable Lifelong Model Editing via Preference Optimization","created":"2026-09-29","cited_by_count":0,"area":"alignment"}],"next_cursor":null}