{"total":142,"rows":[{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2410.18451","title":"Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs","created":"2024-10-24","cited_by_count":327,"area":"lr"},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"area":"alignment"},{"id":"2505.02387","title":"RM-R1: Reward Modeling as Reasoning","created":"2025-05-05","cited_by_count":154,"area":"lr"},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144,"area":null},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"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":"2410.01257","title":"HelpSteer2-Preference: Complementing Ratings with Preferences","created":"2024-10-02","cited_by_count":130,"area":"alignment"},{"id":"2408.11791","title":"Critique-out-Loud Reward Models","created":"2024-08-21","cited_by_count":106,"area":"alignment"},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2402.09345","title":"InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling","created":"2024-02-14","cited_by_count":79,"area":"alignment"},{"id":"2311.14736","title":"Data Diversity Matters for Robust Instruction Tuning","created":"2023-11-21","cited_by_count":76,"area":null},{"id":"2505.11475","title":"HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages","created":"2025-05-16","cited_by_count":75,"area":"alignment"},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2411.16646","title":"Self-Generated Critiques Boost Reward Modeling for Language Models","created":"2024-11-25","cited_by_count":71,"area":"lr"},{"id":"2402.07314","title":"Online Iterative Reinforcement Learning from Human Feedback with General Preference Model","created":"2024-02-11","cited_by_count":52,"area":"alignment"},{"id":"2411.04991","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","created":"2024-11-07","cited_by_count":48,"area":"lr"},{"id":"2505.14674","title":"Reward Reasoning Model","created":"2025-05-20","cited_by_count":47,"area":"lr"},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2409.20370","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","created":"2024-09-30","cited_by_count":43,"area":"alignment"},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","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":"2409.14664","title":"Direct Judgement Preference Optimization","created":"2024-09-23","cited_by_count":33,"area":"alignment"},{"id":"2410.08811","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","created":"2024-10-11","cited_by_count":33,"area":"safety"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2407.09823","title":"NativQA: Multilingual Culturally-Aligned Natural Query for LLMs","created":"2024-07-13","cited_by_count":30,"area":null},{"id":"2502.19148","title":"Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs","created":"2025-02-26","cited_by_count":29,"area":null},{"id":"2603.01562","title":"RubricBench: Aligning Model-Generated Rubrics with Human Standards","created":"2026-03-02","cited_by_count":28,"area":"alignment"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2402.10884","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","created":"2024-02-16","cited_by_count":26,"area":"mllm"},{"id":"2406.05882","title":"Distributional Preference Alignment of LLMs via Optimal Transport","created":"2024-06-09","cited_by_count":26,"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":"2502.11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models","created":"2025-02-17","cited_by_count":22,"area":"alignment"},{"id":"2404.18864","title":"Performance-Aligned LLMs for Generating Fast Code","created":"2024-04-29","cited_by_count":21,"area":null},{"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":"2409.06691","title":"Geometric-Averaged Preference Optimization for Soft Preference Labels","created":"2024-09-10","cited_by_count":18,"area":"alignment"},{"id":"2410.18027","title":"Cross-lingual Transfer of Reward Models in Multilingual Alignment","created":"2024-10-23","cited_by_count":17,"area":"alignment"},{"id":"2502.14354","title":"Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignment","created":"2025-02-20","cited_by_count":16,"area":"lr"},{"id":"2508.10599","title":"Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models","created":"2025-08-14","cited_by_count":16,"area":"mechinterp"},{"id":"2509.04484","title":"The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors","created":"2025-08-31","cited_by_count":16,"area":null},{"id":"2402.07896","title":"Suppressing Pink Elephants with Direct Principle Feedback","created":"2024-02-12","cited_by_count":15,"area":"alignment"},{"id":"2404.03820","title":"CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues","created":"2024-04-04","cited_by_count":15,"area":"lr"},{"id":"2506.12915","title":"PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization","created":"2025-06-15","cited_by_count":15,"area":null},{"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":"2502.10762","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2507.04756","title":"CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering","created":"2025-07-07","cited_by_count":13,"area":null},{"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":"2511.01758","title":"RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks","created":"2025-11-03","cited_by_count":13,"area":"lr"},{"id":"2410.01532","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","created":"2024-10-02","cited_by_count":12,"area":"alignment"},{"id":"2501.02790","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","created":"2025-01-06","cited_by_count":12,"area":"alignment"},{"id":"2603.08035","title":"CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling","created":"2026-03-09","cited_by_count":12,"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":"2510.10205","title":"PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration","created":"2025-10-11","cited_by_count":11,"area":"mechinterp"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2502.13131","title":"Rethinking Diverse Human Preference Learning through Principal Component Analysis","created":"2025-02-18","cited_by_count":10,"area":"lr"},{"id":"2503.01658","title":"CoPL: Collaborative Preference Learning for Personalizing LLMs","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2411.16502","title":"Interpreting Language Reward Models via Contrastive Explanations","created":"2024-11-25","cited_by_count":9,"area":"alignment"},{"id":"2409.06903","title":"Semi-Supervised Reward Modeling via Iterative Self-Training","created":"2024-09-10","cited_by_count":8,"area":"alignment"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2510.08630","title":"ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection","created":"2025-10-08","cited_by_count":8,"area":"lr"},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"id":"2410.23726","title":"Towards Reliable Alignment: Uncertainty-aware RLHF","created":"2024-10-31","cited_by_count":7,"area":"alignment"},{"id":"2503.02989","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","created":"2025-03-04","cited_by_count":7,"area":"alignment"},{"id":"2506.12350","title":"Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory","created":"2025-06-14","cited_by_count":7,"area":"alignment"},{"id":"2601.21872","title":"WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents","created":"2026-01-29","cited_by_count":7,"area":"lr"},{"id":"2602.17633","title":"When to Trust the Cheap Check: Weak and Strong Verification for Reasoning","created":"2026-02-19","cited_by_count":7,"area":"lr"},{"id":"2603.18736","title":"CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks","created":"2026-03-19","cited_by_count":7,"area":"alignment"},{"id":"2408.15339","title":"UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types","created":"2024-08-27","cited_by_count":6,"area":"alignment"},{"id":"2409.11212","title":"Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization","created":"2024-09-17","cited_by_count":6,"area":"alignment"},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6,"area":"alignment"},{"id":"2506.07165","title":"AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models","created":"2025-06-08","cited_by_count":6,"area":"alignment"},{"id":"2510.01167","title":"Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards","created":"2025-10-01","cited_by_count":6,"area":"alignment"},{"id":"2510.19050","title":"Rectifying Shortcut Behaviors in Preference-based Reward Learning","created":"2025-10-21","cited_by_count":6,"area":"alignment"},{"id":"2606.19818","title":"Uncertainty-Aware Reward Modeling for Stable RLHF","created":"2026-06-18","cited_by_count":6,"area":"alignment"},{"id":"2407.01470","title":"DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging","created":"2024-07-01","cited_by_count":5,"area":"alignment"},{"id":"2505.17122","title":"Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?","created":"2025-05-21","cited_by_count":5,"area":"alignment"},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5,"area":"alignment"},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2511.08590","title":"GMTRouter: Personalized LLM Router over Multi-turn User Interactions","created":"2025-10-29","cited_by_count":5,"area":null},{"id":"2511.17579","title":"Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation","created":"2025-11-15","cited_by_count":5,"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":"2503.20995","title":"ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2406.18266","title":"\"Vorbe\\c{s}ti Rom\\^ane\\c{s}te?\" A Recipe to Train Powerful Romanian LLMs with English Instructions","created":"2024-06-26","cited_by_count":3,"area":null},{"id":"2407.04615","title":"On the Low-Rank Parametrization of Reward Models for Controlled Language Generation","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2502.09042","title":"Typhoon T1: An Open Thai Reasoning Model","created":"2025-02-13","cited_by_count":3,"area":"lr"},{"id":"2503.10666","title":"Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2503.10927","title":"OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses","created":"2025-03-13","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":"2510.16255","title":"Detecting Adversarial Fine-tuning with Auditing Agents","created":"2025-10-17","cited_by_count":3,"area":"agents"},{"id":"2510.18849","title":"Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning","created":"2025-10-21","cited_by_count":3,"area":"alignment"},{"id":"2511.12464","title":"Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models","created":"2025-11-16","cited_by_count":3,"area":"alignment"},{"id":"2511.17937","title":"Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria","created":"2025-11-22","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":"2603.16152","title":"HIPO: Instruction Hierarchy via Constrained Reinforcement Learning","created":"2026-03-17","cited_by_count":3,"area":"alignment"},{"id":"2603.23184","title":"ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment","created":"2026-03-24","cited_by_count":3,"area":"alignment"}],"next_cursor":"100"}