{"total":19,"rows":[{"id":"2403.17141","title":"MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models","created":"2024-03-25","cited_by_count":44,"area":"alignment"},{"id":"2505.06274","title":"PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model","created":"2025-05-06","cited_by_count":28,"area":"alignment"},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18,"area":"alignment"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2503.18130","title":"Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization","created":"2025-03-23","cited_by_count":14,"area":"alignment"},{"id":"2406.14393","title":"Jailbreaking as a Reward Misspecification Problem","created":"2024-06-20","cited_by_count":11,"area":"alignment"},{"id":"2407.02987","title":"LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models","created":"2024-07-03","cited_by_count":7,"area":"alignment"},{"id":"2405.20053","title":"Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads","created":"2024-05-30","cited_by_count":5,"area":"alignment"},{"id":"2404.18410","title":"Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting","created":"2024-04-29","cited_by_count":4,"area":"alignment"},{"id":"2510.13212","title":"Towards Understanding Valuable Preference Data for Large Language Model Alignment","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"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":"2407.09447","title":"ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts","created":"2024-07-12","cited_by_count":3,"area":"alignment"},{"id":"2605.01205","title":"SRA: Span Representation Alignment for Large Language Model Distillation","created":"2026-05-02","cited_by_count":3,"area":"alignment"},{"id":"2603.19741","title":"FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment","created":"2026-03-20","cited_by_count":2,"area":"alignment"},{"id":"2505.18952","title":"Online Knowledge Distillation with Reward Guidance","created":"2025-05-25","cited_by_count":0,"area":"alignment"},{"id":"2512.00724","title":"UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking","created":"2025-11-30","cited_by_count":0,"area":"alignment"},{"id":"2608.09605","title":"TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation","created":"2026-08-10","cited_by_count":0,"area":"alignment"}],"next_cursor":null}