{"total":44,"rows":[{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2411.17451","title":"VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models","created":"2024-11-26","cited_by_count":86,"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":"2409.11704","title":"From Lists to Emojis: How Format Bias Affects Model Alignment","created":"2024-09-18","cited_by_count":49,"area":"alignment"},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41,"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":"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":"2406.00888","title":"Aligning Language Models with Demonstrated Feedback","created":"2024-06-02","cited_by_count":34,"area":"alignment"},{"id":"2409.14664","title":"Direct Judgement Preference Optimization","created":"2024-09-23","cited_by_count":33,"area":"alignment"},{"id":"2406.11370","title":"Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments","created":"2024-06-17","cited_by_count":25,"area":"alignment"},{"id":"2504.07532","title":"AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation","created":"2025-04-10","cited_by_count":25,"area":"alignment"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","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":"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":"2606.04923","title":"Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-06-03","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":"2405.17382","title":"ReMoDetect: Reward Models Recognize Aligned LLM's Generations","created":"2024-05-27","cited_by_count":11,"area":"alignment"},{"id":"2406.15352","title":"A SMART Mnemonic Sounds like \"Glue Tonic\": Mixing LLMs with Student Feedback to Make Mnemonic Learning Stick","created":"2024-06-21","cited_by_count":10,"area":"alignment"},{"id":"2511.03369","title":"Silenced Biases: The Dark Side LLMs Learned to Refuse","created":"2025-11-05","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":"2502.13417","title":"RLTHF: Targeted Human Feedback for LLM Alignment","created":"2025-02-19","cited_by_count":8,"area":"alignment"},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"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":"2511.02109","title":"Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences","created":"2025-11-03","cited_by_count":6,"area":"alignment"},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","cited_by_count":5,"area":"alignment"},{"id":"2410.09362","title":"SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins","created":"2024-10-12","cited_by_count":5,"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":"2505.15795","title":"Reverse Engineering Human Preferences with Reinforcement Learning","created":"2025-05-21","cited_by_count":3,"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":"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":"2509.23542","title":"On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2607.01830","title":"Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling","created":"2026-07-02","cited_by_count":3,"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":"2605.04539","title":"RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization","created":"2026-05-06","cited_by_count":2,"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":"2603.16410","title":"PlotTwist: A Creative Plot Generation Framework with Small Language Models","created":"2026-03-17","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":"2605.26878","title":"Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation","created":"2026-05-26","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":"2608.08002","title":"Evaluator Ensembles Under Reward Hacking: Covariance Geometry and Finite-Search Guarantees","created":"2026-08-08","cited_by_count":0,"area":"alignment"},{"id":"2608.30065","title":"Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark","created":"2026-08-30","cited_by_count":0,"area":"alignment"},{"id":"2609.08475","title":"Do Reviewers Still Reward Lexical Complexity? A Frozen-Rater Study of Preference Drift in 124K ICLR Reviews","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.09835","title":"HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization","created":"2026-09-09","cited_by_count":0,"area":"alignment"},{"id":"2610.19832","title":"Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}