{"total":13,"rows":[{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2506.10054","title":"Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs","created":"2025-06-11","cited_by_count":9,"area":"alignment"},{"id":"2511.07896","title":"SparseRM: A Lightweight Preference Modeling with Sparse Autoencoder","created":"2025-11-11","cited_by_count":7,"area":"alignment"},{"id":"2502.14619","title":"Reward Models Identify Consistency, Not Causality","created":"2025-02-20","cited_by_count":6,"area":"alignment"},{"id":"2605.02946","title":"RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2604.13051","title":"The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious","created":"2026-03-17","cited_by_count":5,"area":"alignment"},{"id":"2506.02460","title":"MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework","created":"2025-06-03","cited_by_count":3,"area":"alignment"},{"id":"2509.02133","title":"AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models","created":"2025-09-02","cited_by_count":2,"area":"alignment"},{"id":"2510.07315","title":"SWE-IF: Aligning Code Evaluation with Human Preference","created":"2025-10-08","cited_by_count":2,"area":"alignment"},{"id":"2603.12963","title":"Long-form RewardBench: Evaluating Reward Models for Long-form Generation","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2607.23991","title":"SyRuP: Enhancing System-Prompt Following via Reward-Guided Prediction in LLM Decoding","created":"2026-07-27","cited_by_count":0,"area":"alignment"},{"id":"2609.16589","title":"Do LLMs Have Values? A Quantitative Analysis and Alignment Framework for Values in Large Language Models","created":"2026-09-15","cited_by_count":0,"area":"alignment"}],"next_cursor":null}