{"total":14,"rows":[{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185,"area":"alignment"},{"id":"2310.19347","title":"Improving Factual Consistency of News Summarization by Contrastive Preference Optimization","created":"2023-10-30","cited_by_count":6,"area":"alignment"},{"id":"2503.10093","title":"Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling","created":"2025-03-13","cited_by_count":4,"area":"alignment"},{"id":"2604.18901","title":"Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams","created":"2026-04-20","cited_by_count":4,"area":"alignment"},{"id":"2603.12795","title":"SteerRM: Debiasing Reward Models via Sparse Autoencoders","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2605.01374","title":"MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation","created":"2026-05-02","cited_by_count":2,"area":"alignment"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2606.21645","title":"Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models","created":"2026-06-19","cited_by_count":0,"area":"alignment"},{"id":"2608.03892","title":"Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition","created":"2026-08-04","cited_by_count":0,"area":"alignment"},{"id":"2608.05409","title":"Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment","created":"2026-08-05","cited_by_count":0,"area":"alignment"},{"id":"2608.29978","title":"Evolutionary Soups: Evolving Mixture-of-Experts for Multi-Objective LLM Alignment","created":"2026-08-30","cited_by_count":0,"area":"alignment"},{"id":"2608.30902","title":"Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation","created":"2026-08-31","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"},{"id":"2610.12707","title":"Unsupervised Multimodal Reward Modeling","created":"2026-10-08","cited_by_count":0,"area":"alignment"}],"next_cursor":null}