{"total":55,"rows":[{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236,"area":"alignment"},{"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":"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":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107,"area":"alignment"},{"id":"2404.10271","title":"Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback","created":"2024-04-16","cited_by_count":100,"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":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74,"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":"2405.01481","title":"NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment","created":"2024-05-02","cited_by_count":41,"area":"alignment"},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39,"area":"alignment"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2408.15313","title":"Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models","created":"2024-08-27","cited_by_count":27,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2503.00295","title":"Robust Multi-Objective Preference Alignment with Online DPO","created":"2025-03-01","cited_by_count":22,"area":"alignment"},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"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":"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":"2505.24846","title":"MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning","created":"2025-05-30","cited_by_count":11,"area":"alignment"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","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":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"id":"2410.14676","title":"SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment","created":"2024-10-18","cited_by_count":8,"area":"alignment"},{"id":"2505.04993","title":"Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes","created":"2025-05-08","cited_by_count":7,"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":"2407.16970","title":"Towards Aligning Language Models with Textual Feedback","created":"2024-07-24","cited_by_count":5,"area":"alignment"},{"id":"2504.11337","title":"REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective","created":"2025-04-15","cited_by_count":5,"area":"alignment"},{"id":"2405.17956","title":"Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier","created":"2024-05-28","cited_by_count":4,"area":"alignment"},{"id":"2504.16628","title":"ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data","created":"2025-04-23","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":"2604.12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2405.00578","title":"The Real, the Better: Aligning Large Language Models with Online Human Behaviors","created":"2024-05-01","cited_by_count":3,"area":"alignment"},{"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":"2410.06965","title":"Uncovering Factor Level Preferences to Improve Human-Model Alignment","created":"2024-10-09","cited_by_count":2,"area":"alignment"},{"id":"2410.19206","title":"Inference time LLM alignment in single and multidomain preference spectrum","created":"2024-10-24","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":"2601.14032","title":"RM-Distiller: Exploiting Generative LLM for Reward Model Distillation","created":"2026-01-20","cited_by_count":2,"area":"alignment"},{"id":"2601.13669","title":"CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks","created":"2026-01-20","cited_by_count":1,"area":"alignment"},{"id":"2602.01128","title":"Tangent Space Fine-Tuning for Directional Preference Alignment in Large Language Models","created":"2026-02-01","cited_by_count":1,"area":"alignment"},{"id":"2507.09060","title":"CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment","created":"2025-07-11","cited_by_count":0,"area":"alignment"},{"id":"2508.05165","title":"Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models","created":"2025-08-07","cited_by_count":0,"area":"alignment"},{"id":"2604.01312","title":"Preference learning in shades of gray: Interpretable and bias-aware reward modeling for human preferences","created":"2026-04-01","cited_by_count":0,"area":"alignment"},{"id":"2604.01787","title":"DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment","created":"2026-04-02","cited_by_count":0,"area":"alignment"},{"id":"2604.15577","title":"Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"id":"2605.16345","title":"Goal-Conditioned Supervised Learning for LLM Fine-Tuning","created":"2026-05-08","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":"2605.30487","title":"Configurable Reward Model for Balanced Safety Alignment","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2605.30873","title":"Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2606.13209","title":"Understanding helpfulness and harmless tension in reward models","created":"2026-06-11","cited_by_count":0,"area":"alignment"},{"id":"2606.13227","title":"PolyAlign: Conditional Human-Distribution Alignment","created":"2026-06-11","cited_by_count":0,"area":"alignment"},{"id":"2608.30197","title":"ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2610.04845","title":"Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution","created":"2026-10-04","cited_by_count":0,"area":"alignment"}],"next_cursor":null}