{"total":132,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2510.07743","title":"OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment","created":"2025-10-09","cited_by_count":132,"area":"alignment"},{"id":"2405.08448","title":"Understanding the performance gap between online and offline alignment algorithms","created":"2024-05-14","cited_by_count":110,"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":"2408.13006","title":"Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates","created":"2024-08-23","cited_by_count":72,"area":"alignment"},{"id":"2602.01511","title":"Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training","created":"2026-02-02","cited_by_count":54,"area":"alignment"},{"id":"2509.21500","title":"Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training","created":"2025-09-25","cited_by_count":53,"area":"alignment"},{"id":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2403.19270","title":"sDPO: Don't Use Your Data All at Once","created":"2024-03-28","cited_by_count":46,"area":"alignment"},{"id":"2407.02273","title":"Language Model Alignment in Multilingual Trolley Problems","created":"2024-07-02","cited_by_count":46,"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":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41,"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":"2505.17147","title":"MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming","created":"2025-05-22","cited_by_count":32,"area":"alignment"},{"id":"2406.12935","title":"ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates","created":"2024-06-17","cited_by_count":30,"area":"alignment"},{"id":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30,"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":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2407.13709","title":"Understanding Reference Policies in Direct Preference Optimization","created":"2024-07-18","cited_by_count":22,"area":"alignment"},{"id":"2505.23749","title":"Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?","created":"2025-05-29","cited_by_count":22,"area":"alignment"},{"id":"2405.12739","title":"SPO: Multi-Dimensional Preference Sequential Alignment With Implicit Reward Modeling","created":"2024-05-21","cited_by_count":21,"area":"alignment"},{"id":"2503.16669","title":"Aligning Text-to-Music Evaluation with Human Preferences","created":"2025-03-20","cited_by_count":21,"area":"alignment"},{"id":"2410.16714","title":"Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment","created":"2024-10-22","cited_by_count":20,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"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":"2501.00560","title":"Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference","created":"2024-12-31","cited_by_count":16,"area":"alignment"},{"id":"2407.10944","title":"Naturally Occurring Feedback is Common, Extractable and Useful","created":"2024-07-15","cited_by_count":14,"area":"alignment"},{"id":"2412.02685","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","created":"2024-12-03","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":"2506.05339","title":"Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models","created":"2025-06-05","cited_by_count":13,"area":"alignment"},{"id":"2410.07304","title":"The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making","created":"2024-10-09","cited_by_count":12,"area":"alignment"},{"id":"2411.12762","title":"Playing Language Game with LLMs Leads to Jailbreaking","created":"2024-11-16","cited_by_count":11,"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":"2406.16316","title":"Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?","created":"2024-06-24","cited_by_count":10,"area":"alignment"},{"id":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","cited_by_count":10,"area":"alignment"},{"id":"2411.09947","title":"LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuning","created":"2024-11-15","cited_by_count":10,"area":"alignment"},{"id":"2506.07326","title":"Reward Model Interpretability via Optimal and Pessimal Tokens","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2509.01301","title":"Culture is Everywhere: A Call for Intentionally Cultural Evaluation","created":"2025-09-01","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":"2503.04647","title":"Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment","created":"2025-03-06","cited_by_count":9,"area":"alignment"},{"id":"2506.06636","title":"SafeLawBench: Towards Safe Alignment of Large Language Models","created":"2025-06-07","cited_by_count":9,"area":"alignment"},{"id":"2603.18507","title":"Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM","created":"2026-03-19","cited_by_count":9,"area":"alignment"},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2412.11385","title":"Why Does ChatGPT \"Delve\" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models","created":"2024-12-16","cited_by_count":8,"area":"alignment"},{"id":"2407.15229","title":"A Practical Analysis of Human Alignment with *PO","created":"2024-07-21","cited_by_count":7,"area":"alignment"},{"id":"2502.10563","title":"Accelerating Unbiased LLM Evaluation via Synthetic Feedback","created":"2025-02-14","cited_by_count":7,"area":"alignment"},{"id":"2504.19342","title":"Contextual Online Uncertainty-Aware Preference Learning for Human Feedback","created":"2025-04-27","cited_by_count":7,"area":"alignment"},{"id":"2604.07343","title":"Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization","created":"2026-04-08","cited_by_count":7,"area":"alignment"},{"id":"2606.13685","title":"The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation","created":"2026-04-23","cited_by_count":7,"area":"alignment"},{"id":"2409.13948","title":"Aligning Language Models Using Follow-up Likelihood as Reward Signal","created":"2024-09-20","cited_by_count":6,"area":"alignment"},{"id":"2410.04834","title":"As Simple as Fine-tuning: LLM Alignment via Bidirectional Negative Feedback Loss","created":"2024-10-07","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":"2505.02363","title":"SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning","created":"2025-05-05","cited_by_count":6,"area":"alignment"},{"id":"2509.18632","title":"A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users","created":"2025-09-23","cited_by_count":6,"area":"alignment"},{"id":"2510.14616","title":"Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures","created":"2025-10-16","cited_by_count":6,"area":"alignment"},{"id":"2511.12573","title":"Mitigating Length Bias in RLHF through a Causal Lens","created":"2025-11-16","cited_by_count":6,"area":"alignment"},{"id":"2410.06293","title":"Accelerated Preference Optimization for Large Language Model Alignment","created":"2024-10-08","cited_by_count":5,"area":"alignment"},{"id":"2411.03700","title":"The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models","created":"2024-11-06","cited_by_count":5,"area":"alignment"},{"id":"2504.02193","title":"More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment","created":"2025-04-03","cited_by_count":5,"area":"alignment"},{"id":"2506.02553","title":"Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective","created":"2025-06-03","cited_by_count":5,"area":"alignment"},{"id":"2506.03968","title":"From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding","created":"2025-06-04","cited_by_count":5,"area":"alignment"},{"id":"2509.08858","title":"Decentralising LLM Alignment: A Case for Context, Pluralism, and Participation","created":"2025-09-09","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":"2601.02986","title":"P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist","created":"2026-01-06","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":"2605.09702","title":"Calibrate, Don't Curate: Label-Efficient Estimation from Noisy LLM Judges","created":"2026-05-10","cited_by_count":5,"area":"alignment"},{"id":"2410.02451","title":"Strong Preferences Affect the Robustness of Preference Models and Value Alignment","created":"2024-10-03","cited_by_count":4,"area":"alignment"},{"id":"2501.18511","title":"WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training","created":"2025-01-30","cited_by_count":4,"area":"alignment"},{"id":"2502.11284","title":"Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning","created":"2025-02-16","cited_by_count":4,"area":"alignment"},{"id":"2509.18531","title":"No Verifiable Reward for Prosody: Toward Preference-Guided Prosody Learning in TTS","created":"2025-09-23","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":"2602.13576","title":"Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges","created":"2026-02-14","cited_by_count":4,"area":"alignment"},{"id":"2603.03336","title":"Prompt-Dependent Ranking of Large Language Models with Uncertainty Quantification","created":"2026-02-11","cited_by_count":4,"area":"alignment"},{"id":"2505.19176","title":"Assistant-Guided Mitigation of Teacher Preference Bias in LLM-as-a-Judge","created":"2025-05-25","cited_by_count":3,"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":"2506.14157","title":"DCRM: A Heuristic to Measure Response Pair Quality in Preference Optimization","created":"2025-06-17","cited_by_count":3,"area":"alignment"},{"id":"2508.16982","title":"Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens","created":"2025-08-23","cited_by_count":3,"area":"alignment"},{"id":"2511.20604","title":"On Evaluating LLM Alignment by Evaluating LLMs as Judges","created":"2025-11-25","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":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","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":"2410.06965","title":"Uncovering Factor Level Preferences to Improve Human-Model Alignment","created":"2024-10-09","cited_by_count":2,"area":"alignment"},{"id":"2410.13785","title":"PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment","created":"2024-10-17","cited_by_count":2,"area":"alignment"},{"id":"2501.03271","title":"DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization","created":"2025-01-05","cited_by_count":2,"area":"alignment"},{"id":"2505.20088","title":"Multi-Domain Explainability of Preferences","created":"2025-05-26","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":"2510.09333","title":"Efficient Bayesian Inference from Noisy Pairwise Comparisons","created":"2025-10-10","cited_by_count":2,"area":"alignment"},{"id":"2602.06669","title":"compar:IA: The French Government's LLM arena to collect French-language human prompts and preference data","created":"2026-02-06","cited_by_count":2,"area":"alignment"},{"id":"2602.09653","title":"ClinAlign: Scaling Healthcare Alignment from Clinician Preference","created":"2026-02-10","cited_by_count":2,"area":"alignment"},{"id":"2605.25998","title":"Causal methods for LLM development and evaluation","created":"2026-05-25","cited_by_count":2,"area":"alignment"},{"id":"2608.19802","title":"Stopping and Routing LLM Judge Panels","created":"2026-08-20","cited_by_count":2,"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":"2508.08486","title":"Beyond Ordinal Preferences: Why Alignment Needs Cardinal Human Feedback","created":"2025-08-11","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":"2509.00673","title":"Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection","created":"2025-08-31","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":"2510.15514","title":"Voting with the Graph: Stable RLAIF via Topological Consistency Maximization","created":"2025-10-17","cited_by_count":1,"area":"alignment"}],"next_cursor":"100"}