{"total":16,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759,"area":"alignment"},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723,"area":"alignment"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"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":"2403.05612","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","created":"2024-03-08","cited_by_count":87,"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":"2311.14743","title":"A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift","created":"2023-11-21","cited_by_count":18,"area":"alignment"},{"id":"2404.01863","title":"Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models","created":"2024-04-02","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":"2408.07772","title":"Out-of-Distribution Learning with Human Feedback","created":"2024-08-14","cited_by_count":6,"area":"alignment"},{"id":"2509.25509","title":"Can Molecular Foundation Models Know What They Don't Know? A Simple Remedy with Preference Optimization","created":"2025-09-29","cited_by_count":2,"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":"2605.07172","title":"Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2608.13345","title":"Rules or Character? Scaling Laws for AI Safety Design","created":"2026-08-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}