{"total":81,"rows":[{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724,"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":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467,"area":"alignment"},{"id":"2507.18624","title":"Checklists Are Better Than Reward Models For Aligning Language Models","created":"2025-07-24","cited_by_count":128,"area":"alignment"},{"id":"2407.10490","title":"Learning Dynamics of LLM Finetuning","created":"2024-07-15","cited_by_count":95,"area":"alignment"},{"id":"2310.14558","title":"AlpaCare:Instruction-tuned Large Language Models for Medical Application","created":"2023-10-23","cited_by_count":90,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2310.13798","title":"Specific versus General Principles for Constitutional AI","created":"2023-10-20","cited_by_count":47,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39,"area":"alignment"},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39,"area":"alignment"},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2406.17692","title":"From Distributional to Overton Pluralism: Investigating Large Language Model Alignment","created":"2024-06-25","cited_by_count":33,"area":"alignment"},{"id":"2402.03749","title":"Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models","created":"2024-02-06","cited_by_count":28,"area":"alignment"},{"id":"2603.12273","title":"Aligning Language Models from User Interactions","created":"2026-02-18","cited_by_count":28,"area":"alignment"},{"id":"2407.06443","title":"Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment","created":"2024-07-08","cited_by_count":25,"area":"alignment"},{"id":"2406.19774","title":"Direct Preference Knowledge Distillation for Large Language Models","created":"2024-06-28","cited_by_count":21,"area":"alignment"},{"id":"2406.02764","title":"Adaptive Preference Scaling for Reinforcement Learning with Human Feedback","created":"2024-06-04","cited_by_count":20,"area":"alignment"},{"id":"2409.08813","title":"Your Weak LLM is Secretly a Strong Teacher for Alignment","created":"2024-09-13","cited_by_count":20,"area":"alignment"},{"id":"2503.08619","title":"LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization","created":"2025-03-11","cited_by_count":20,"area":"alignment"},{"id":"2402.10893","title":"RLVF: Learning from Verbal Feedback without Overgeneralization","created":"2024-02-16","cited_by_count":19,"area":"alignment"},{"id":"2503.02832","title":"AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation","created":"2025-03-04","cited_by_count":17,"area":"alignment"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2607.15161","title":"On-Policy Delta Distillation","created":"2026-07-16","cited_by_count":15,"area":"alignment"},{"id":"2210.07652","title":"Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values","created":"2022-10-14","cited_by_count":13,"area":"alignment"},{"id":"2605.07396","title":"Rubric-based On-policy Distillation","created":"2026-05-08","cited_by_count":13,"area":"alignment"},{"id":"2411.05986","title":"Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappings","created":"2024-11-08","cited_by_count":11,"area":"alignment"},{"id":"2411.12843","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","created":"2024-11-19","cited_by_count":11,"area":"alignment"},{"id":"2512.23126","title":"InSPO: Unlocking Intrinsic Self-Reflection for LLM Preference Optimization","created":"2025-12-29","cited_by_count":11,"area":"alignment"},{"id":"2311.18495","title":"Improving Adversarial Transferability via Model Alignment","created":"2023-11-30","cited_by_count":10,"area":"alignment"},{"id":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10,"area":"alignment"},{"id":"2402.08005","title":"Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs","created":"2024-02-12","cited_by_count":10,"area":"alignment"},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2309.08583","title":"ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer","created":"2023-09-15","cited_by_count":5,"area":"alignment"},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2410.08458","title":"Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both","created":"2024-10-11","cited_by_count":5,"area":"alignment"},{"id":"2502.17927","title":"Advantage-Guided Distillation for Preference Alignment in Small Language Models","created":"2025-02-25","cited_by_count":5,"area":"alignment"},{"id":"2403.15469","title":"Isometric Neural Machine Translation using Phoneme Count Ratio Reward-based Reinforcement Learning","created":"2024-03-20","cited_by_count":4,"area":"alignment"},{"id":"2408.00307","title":"ABC Align: Large Language Model Alignment for Safety & Accuracy","created":"2024-08-01","cited_by_count":4,"area":"alignment"},{"id":"2512.09403","title":"Black-Box Behavioral Distillation Breaks Safety Alignment in Medical LLMs","created":"2025-12-10","cited_by_count":4,"area":"alignment"},{"id":"2601.20687","title":"Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models","created":"2026-01-28","cited_by_count":4,"area":"alignment"},{"id":"2602.11157","title":"Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety","created":"2025-12-08","cited_by_count":4,"area":"alignment"},{"id":"2606.09076","title":"Z-Reward: Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions","created":"2026-06-08","cited_by_count":4,"area":"alignment"},{"id":"2405.07004","title":"Stealthy Imitation: Reward-guided Environment-free Policy Stealing","created":"2024-05-11","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":"2412.02125","title":"Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies","created":"2024-12-03","cited_by_count":3,"area":"alignment"},{"id":"2506.15717","title":"daDPO: Distribution-Aware DPO for Distilling Conversational Abilities","created":"2025-06-03","cited_by_count":3,"area":"alignment"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","cited_by_count":3,"area":"alignment"},{"id":"2510.18913","title":"ADPO: Anchored Direct Preference Optimization","created":"2025-10-21","cited_by_count":3,"area":"alignment"},{"id":"2601.11865","title":"CTPD: Cross Tokenizer Preference Distillation","created":"2026-01-17","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":"2608.03092","title":"SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation","created":"2026-08-04","cited_by_count":3,"area":"alignment"},{"id":"2608.11698","title":"REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation","created":"2026-08-12","cited_by_count":3,"area":"alignment"},{"id":"2410.00508","title":"FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization","created":"2024-10-01","cited_by_count":2,"area":"alignment"},{"id":"2505.18799","title":"ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models","created":"2025-05-24","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":"2506.04464","title":"Leveraging Reward Models for Guiding Code Review Comment Generation","created":"2025-06-04","cited_by_count":1,"area":"alignment"},{"id":"2506.06444","title":"Saffron-1: Safety Inference Scaling","created":"2025-06-06","cited_by_count":1,"area":"alignment"},{"id":"2601.22513","title":"Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models","created":"2026-01-30","cited_by_count":1,"area":"alignment"},{"id":"2608.06526","title":"GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimization","created":"2026-08-06","cited_by_count":1,"area":"alignment"},{"id":"2406.14208","title":"SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots","created":"2024-06-20","cited_by_count":0,"area":"alignment"},{"id":"2505.18952","title":"Online Knowledge Distillation with Reward Guidance","created":"2025-05-25","cited_by_count":0,"area":"alignment"},{"id":"2509.16965","title":"Preference Distillation via Value based Reinforcement Learning","created":"2025-09-21","cited_by_count":0,"area":"alignment"},{"id":"2510.12014","title":"Embedding the Teacher: Distilling vLLM Preferences for Scalable Image Retrieval","created":"2025-10-13","cited_by_count":0,"area":"alignment"},{"id":"2512.06920","title":"Parent-Guided Semantic Reward Model (PGSRM): Embedding-Based Reward Functions for Reinforcement Learning of Transformer Language Models","created":"2025-12-07","cited_by_count":0,"area":"alignment"},{"id":"2512.17180","title":"Conservative Bias in Multi-Teacher Learning: Why Agents Prefer Low-Reward Advisors","created":"2025-12-19","cited_by_count":0,"area":"alignment"},{"id":"2601.09718","title":"StatLLaMA: Multi-Stage training for domain-optimized statistical large language models","created":"2025-12-26","cited_by_count":0,"area":"alignment"},{"id":"2603.16622","title":"Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model","created":"2026-03-17","cited_by_count":0,"area":"alignment"},{"id":"2605.21558","title":"From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2605.25629","title":"When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift","created":"2026-05-25","cited_by_count":0,"area":"alignment"},{"id":"2606.08032","title":"Variational Proximal Policy Optimization","created":"2026-06-06","cited_by_count":0,"area":"alignment"},{"id":"2606.26787","title":"AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing","created":"2026-06-25","cited_by_count":0,"area":"alignment"},{"id":"2607.07859","title":"Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning","created":"2026-07-08","cited_by_count":0,"area":"alignment"},{"id":"2609.30802","title":"Understanding the Role of Prompt Template in Knowledge Distillation for Safety Alignment","created":"2026-09-25","cited_by_count":0,"area":"alignment"},{"id":"2610.03185","title":"Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective","created":"2026-10-02","cited_by_count":0,"area":"alignment"},{"id":"2610.09209","title":"Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation","created":"2026-10-06","cited_by_count":0,"area":"alignment"},{"id":"2610.18766","title":"Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges","created":"2026-10-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}