{"total":110,"rows":[{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"area":"alignment"},{"id":"2310.08491","title":"Prometheus: Inducing Fine-grained Evaluation Capability in Language Models","created":"2023-10-12","cited_by_count":575,"area":"alignment"},{"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":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2403.16950","title":"Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators","created":"2024-03-25","cited_by_count":149,"area":"alignment"},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72,"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":"2311.18743","title":"AlignBench: Benchmarking Chinese Alignment of Large Language Models","created":"2023-11-30","cited_by_count":68,"area":"alignment"},{"id":"2402.06147","title":"DeAL: Decoding-time Alignment for Large Language Models","created":"2024-02-05","cited_by_count":55,"area":"alignment"},{"id":"2306.10968","title":"BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models","created":"2023-06-19","cited_by_count":42,"area":"alignment"},{"id":"2507.00769","title":"LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing","created":"2025-07-01","cited_by_count":42,"area":"alignment"},{"id":"2309.00754","title":"Efficient RLHF: Reducing the Memory Usage of PPO","created":"2023-09-01","cited_by_count":40,"area":"alignment"},{"id":"2311.09336","title":"LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback","created":"2023-11-15","cited_by_count":39,"area":"alignment"},{"id":"2511.00222","title":"Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning","created":"2025-10-31","cited_by_count":39,"area":"alignment"},{"id":"2410.17578","title":"MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models","created":"2024-10-23","cited_by_count":35,"area":"alignment"},{"id":"2402.15754","title":"HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition","created":"2024-02-24","cited_by_count":33,"area":"alignment"},{"id":"2409.14664","title":"Direct Judgement Preference Optimization","created":"2024-09-23","cited_by_count":33,"area":"alignment"},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32,"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":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"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":"2410.13116","title":"Learning to Summarize from LLM-generated Feedback","created":"2024-10-17","cited_by_count":24,"area":"alignment"},{"id":"2411.01834","title":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback","created":"2024-11-04","cited_by_count":23,"area":"alignment"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2311.02775","title":"AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs","created":"2023-11-05","cited_by_count":22,"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":"2501.11549","title":"Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas","created":"2025-01-20","cited_by_count":19,"area":"alignment"},{"id":"2405.19744","title":"X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions","created":"2024-05-30","cited_by_count":18,"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":"2403.00199","title":"Improving Socratic Question Generation using Data Augmentation and Preference Optimization","created":"2024-03-01","cited_by_count":16,"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":"2508.03550","title":"Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations","created":"2025-08-05","cited_by_count":15,"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":"2310.16271","title":"CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment","created":"2023-10-25","cited_by_count":13,"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":"2510.20369","title":"Ask a Strong LLM Judge when Your Reward Model is Uncertain","created":"2025-10-23","cited_by_count":13,"area":"alignment"},{"id":"2403.03419","title":"Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization","created":"2024-03-06","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":"2604.22891","title":"Quantifying and Mitigating Self-Preference Bias of LLM Judges","created":"2026-04-24","cited_by_count":10,"area":"alignment"},{"id":"2408.15625","title":"CBF-LLM: Safe Control for LLM Alignment","created":"2024-08-28","cited_by_count":9,"area":"alignment"},{"id":"2409.00162","title":"Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback","created":"2024-08-30","cited_by_count":9,"area":"alignment"},{"id":"2409.19715","title":"Coffee-Gym: An Environment for Evaluating and Improving Natural Language Feedback on Erroneous Code","created":"2024-09-29","cited_by_count":9,"area":"alignment"},{"id":"2506.13901","title":"Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations","created":"2025-06-16","cited_by_count":8,"area":"alignment"},{"id":"2408.03618","title":"A Logical Fallacy-Informed Framework for Argument Generation","created":"2024-08-07","cited_by_count":7,"area":"alignment"},{"id":"2505.01903","title":"LookAlike: Consistent Distractor Generation in Math MCQs","created":"2025-05-03","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":"2406.00303","title":"Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning","created":"2024-06-01","cited_by_count":6,"area":"alignment"},{"id":"2508.04698","title":"FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data","created":"2025-08-06","cited_by_count":6,"area":"alignment"},{"id":"2501.13264","title":"OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation","created":"2025-01-22","cited_by_count":5,"area":"alignment"},{"id":"2605.29156","title":"RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains","created":"2026-05-27","cited_by_count":5,"area":"alignment"},{"id":"2308.06385","title":"ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF","created":"2023-08-11","cited_by_count":4,"area":"alignment"},{"id":"2602.08259","title":"A Statistical Framework for Alignment with Biased AI Feedback","created":"2026-02-09","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":"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":"2310.13385","title":"Tuna: Instruction Tuning using Feedback from Large Language Models","created":"2023-10-20","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":"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":"2509.23542","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":"2510.19325","title":"Balancing Rewards in Text Summarization: Multi-Objective Reinforcement Learning via HyperVolume Optimization","created":"2025-10-22","cited_by_count":3,"area":"alignment"},{"id":"2603.16152","title":"HIPO: Instruction Hierarchy via Constrained Reinforcement Learning","created":"2026-03-17","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":"2406.11190","title":"Aligning Large Language Models from Self-Reference AI Feedback with one General Principle","created":"2024-06-17","cited_by_count":2,"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":"2501.12698","title":"Training Dialogue Systems by AI Feedback for Improving Overall Dialogue Impression","created":"2025-01-22","cited_by_count":2,"area":"alignment"},{"id":"2503.04910","title":"Maximizing Signal in Human-Model Preference Alignment","created":"2025-03-06","cited_by_count":2,"area":"alignment"},{"id":"2512.11838","title":"D-STEER - Preference Alignment Techniques Learn to Behave, not to Believe -- Beneath the Surface, DPO as Steering Vector Perturbation in Activation Space","created":"2025-12-03","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":"2601.07149","title":"Rewarding Creativity: A Human-Aligned Generative Reward Model for Reinforcement Learning in Storytelling","created":"2026-01-12","cited_by_count":2,"area":"alignment"},{"id":"2604.08326","title":"ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection","created":"2026-04-09","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":"2606.01196","title":"Low-Resource Safety Failures Are Action Failures, Not Representation Failures","created":"2026-05-31","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":"2402.15473","title":"Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarization","created":"2024-02-23","cited_by_count":1,"area":"alignment"},{"id":"2512.17920","title":"Separating Constraint Compliance from Semantic Accuracy: A Novel Benchmark for Evaluating Instruction-Following Under Compression","created":"2025-12-02","cited_by_count":1,"area":"alignment"},{"id":"2604.20996","title":"AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models","created":"2026-04-22","cited_by_count":1,"area":"alignment"},{"id":"2605.04831","title":"StoryAlign: Evaluating and Training Reward Models for Story Generation","created":"2026-05-06","cited_by_count":1,"area":"alignment"},{"id":"2606.11127","title":"Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation","created":"2026-06-09","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":"2609.09764","title":"SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design","created":"2026-09-09","cited_by_count":1,"area":"alignment"},{"id":"2505.16003","title":"SLMEval: Entropy-Based Calibration for Human-Aligned Evaluation of Large Language Models","created":"2025-05-21","cited_by_count":0,"area":"alignment"},{"id":"2508.02063","title":"TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs","created":"2025-08-04","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":"2511.03121","title":"Control Barrier Function for Aligning Large Language Models","created":"2025-11-05","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":"2601.22385","title":"SP^2DPO: An LLM-assisted Semantic Per-Pair DPO Generalization","created":"2026-01-29","cited_by_count":0,"area":"alignment"},{"id":"2602.15854","title":"Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization","created":"2026-01-24","cited_by_count":0,"area":"alignment"},{"id":"2602.23603","title":"LFQA-HP-1M: A Large-Scale Human Preference Dataset for Long-Form Question Answering","created":"2026-02-27","cited_by_count":0,"area":"alignment"},{"id":"2603.03054","title":"PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2603.12565","title":"Speech-Worthy Alignment for Japanese SpeechLLMs via Direct Preference Optimization","created":"2026-03-13","cited_by_count":0,"area":"alignment"},{"id":"2603.18637","title":"MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment","created":"2026-03-19","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":"2604.05517","title":"UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning","created":"2026-04-07","cited_by_count":0,"area":"alignment"},{"id":"2605.04972","title":"Why Expert Alignment Is Hard: Evidence from Subjective Evaluation","created":"2026-05-06","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":"2605.26878","title":"Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation","created":"2026-05-26","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}