{"total":43,"rows":[{"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":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401,"area":"alignment"},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2402.01694","title":"ARGS: Alignment as Reward-Guided Search","created":"2024-01-23","cited_by_count":103,"area":"alignment"},{"id":"2404.17546","title":"Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo","created":"2024-04-26","cited_by_count":90,"area":"alignment"},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79,"area":"alignment"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2404.16792","title":"Model Extrapolation Expedites Alignment","created":"2024-04-25","cited_by_count":37,"area":"alignment"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2405.19262","title":"Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models","created":"2024-05-29","cited_by_count":32,"area":"alignment"},{"id":"2406.16235","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","created":"2024-06-23","cited_by_count":31,"area":"alignment"},{"id":"2406.12274","title":"SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models","created":"2024-06-18","cited_by_count":23,"area":"alignment"},{"id":"2401.07382","title":"Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation","created":"2024-01-14","cited_by_count":22,"area":"alignment"},{"id":"2409.17819","title":"Inference-Time Language Model Alignment via Integrated Value Guidance","created":"2024-09-26","cited_by_count":19,"area":"alignment"},{"id":"2202.09662","title":"Reward Modeling for Mitigating Toxicity in Transformer-based Language Models","created":"2022-02-19","cited_by_count":18,"area":"alignment"},{"id":"2403.03419","title":"Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization","created":"2024-03-06","cited_by_count":11,"area":"alignment"},{"id":"2510.01243","title":"Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing","created":"2025-09-24","cited_by_count":10,"area":"alignment"},{"id":"2408.05094","title":"Unlocking Decoding-time Controllability: Gradient-Free Multi-Objective Alignment with Contrastive Prompts","created":"2024-08-09","cited_by_count":9,"area":"alignment"},{"id":"2410.03818","title":"Large Language Models can be Strong Self-Detoxifiers","created":"2024-10-04","cited_by_count":7,"area":"alignment"},{"id":"2407.16970","title":"Towards Aligning Language Models with Textual Feedback","created":"2024-07-24","cited_by_count":5,"area":"alignment"},{"id":"2406.11581","title":"Style Transfer with Multi-iteration Preference Optimization","created":"2024-06-17","cited_by_count":4,"area":"alignment"},{"id":"2407.04615","title":"On the Low-Rank Parametrization of Reward Models for Controlled Language Generation","created":"2024-07-05","cited_by_count":3,"area":"alignment"},{"id":"2510.04773","title":"Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning","created":"2025-10-06","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":"2406.16377","title":"On the Transformations across Reward Model, Parameter Update, and In-Context Prompt","created":"2024-06-24","cited_by_count":1,"area":"alignment"},{"id":"2509.16475","title":"Towards Universal Debiasing for Language Models-based Tabular Data Generation","created":"2025-09-20","cited_by_count":1,"area":"alignment"},{"id":"2602.07799","title":"Fairness Aware Reward Optimization","created":"2026-02-08","cited_by_count":1,"area":"alignment"},{"id":"2605.21225","title":"PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment","created":"2026-05-20","cited_by_count":1,"area":"alignment"},{"id":"2607.12985","title":"Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs","created":"2026-07-14","cited_by_count":1,"area":"alignment"},{"id":"2607.29246","title":"Don't Mix Rewards, Mix Policies: Policy Decomposition and Optimization for Multi-Reward RL","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2609.05968","title":"Test-Time Weak-to-Strong Alignment: Transferring Implicit Rewards from Weak to Strong Flow Models","created":"2026-09-05","cited_by_count":1,"area":"alignment"},{"id":"2406.10203","title":"A Probability--Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors","created":"2024-06-14","cited_by_count":0,"area":"alignment"},{"id":"2507.05660","title":"Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI","created":"2025-07-08","cited_by_count":0,"area":"alignment"},{"id":"2602.00619","title":"Jailbreaking LLMs via Calibration","created":"2026-01-31","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":"2605.11712","title":"Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance","created":"2026-05-12","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":"2606.30339","title":"REAR: Test-time Preference Realignment through Reward Decomposition","created":"2026-06-29","cited_by_count":0,"area":"alignment"},{"id":"2609.00624","title":"Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.22359","title":"Resist, Update, Reject: Preference Optimization Installs a Prior-Dependent Reliability Switch","created":"2026-07-26","cited_by_count":0,"area":"alignment"},{"id":"2609.30226","title":"PoEM: Predicting RL Outcomes from Existing Policies","created":"2026-09-24","cited_by_count":0,"area":"alignment"},{"id":"2609.35201","title":"From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}