{"total":26,"rows":[{"id":"2403.04132","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","created":"2024-03-07","cited_by_count":1184,"area":"alignment"},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729,"area":"alignment"},{"id":"2406.15513","title":"PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference","created":"2024-06-20","cited_by_count":261,"area":"alignment"},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"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":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","cited_by_count":15,"area":"alignment"},{"id":"2509.07150","title":"PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design","created":"2025-09-08","cited_by_count":14,"area":"alignment"},{"id":"2412.16974","title":"Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs","created":"2024-12-22","cited_by_count":11,"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":"2504.12911","title":"Benchmarking Multi-National Value Alignment for Large Language Models","created":"2025-04-17","cited_by_count":7,"area":"alignment"},{"id":"2405.16964","title":"Exploring the LLM Journey from Cognition to Expression with Linear Representations","created":"2024-05-27","cited_by_count":5,"area":"alignment"},{"id":"2412.19396","title":"Comparing Few to Rank Many: Active Human Preference Learning using Randomized Frank-Wolfe","created":"2024-12-27","cited_by_count":5,"area":"alignment"},{"id":"2603.12595","title":"Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback","created":"2026-03-13","cited_by_count":5,"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":"2604.03867","title":"Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment","created":"2026-04-04","cited_by_count":3,"area":"alignment"},{"id":"2603.14355","title":"Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling","created":"2026-03-15","cited_by_count":2,"area":"alignment"},{"id":"2405.09747","title":"NIFTY Financial News Headlines Dataset","created":"2024-05-16","cited_by_count":1,"area":"alignment"},{"id":"2505.12322","title":"Model alignment using inter-modal bridges","created":"2025-05-18","cited_by_count":1,"area":"alignment"},{"id":"2510.07557","title":"Investigating Thematic Patterns and User Preferences in LLM Interactions using BERTopic","created":"2025-10-08","cited_by_count":1,"area":"alignment"},{"id":"2601.12758","title":"VISPA: Pluralistic Alignment via Automatic Value Selection and Activation","created":"2026-01-19","cited_by_count":1,"area":"alignment"},{"id":"2603.27971","title":"Principal Prototype Analysis on Manifold for Interpretable Reinforcement Learning","created":"2026-03-30","cited_by_count":0,"area":"alignment"},{"id":"2606.08893","title":"Cheap Reward Hacking Detection","created":"2026-06-08","cited_by_count":0,"area":"alignment"},{"id":"2606.29097","title":"TrafficAlign: Aligning Large Language Models for Traffic Scenario Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2607.05401","title":"Catalyst Papers in Artificial Intelligence Research: A Landscape on ICLR from 2017 to 2025","created":"2026-05-24","cited_by_count":0,"area":"alignment"},{"id":"2610.01821","title":"Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models","created":"2026-10-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}