{"total":81,"rows":[{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"id":"2411.17451","title":"VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models","created":"2024-11-26","cited_by_count":86,"area":"alignment"},{"id":"2410.09893","title":"RMB: Comprehensively Benchmarking Reward Models in LLM Alignment","created":"2024-10-13","cited_by_count":61,"area":"alignment"},{"id":"2412.04814","title":"LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment","created":"2024-12-06","cited_by_count":53,"area":"alignment"},{"id":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2409.11239","title":"LLM-as-a-Judge & Reward Model: What They Can and Cannot Do","created":"2024-09-17","cited_by_count":32,"area":"alignment"},{"id":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32,"area":"alignment"},{"id":"2410.03742","title":"Beyond Scalar Reward Model: Learning Generative Judge from Preference Data","created":"2024-10-01","cited_by_count":32,"area":"alignment"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2506.03637","title":"RewardAnything: Generalizable Principle-Following Reward Models","created":"2025-06-04","cited_by_count":28,"area":"alignment"},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2503.02846","title":"Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs","created":"2025-03-04","cited_by_count":24,"area":"alignment"},{"id":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2512.24551","title":"PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation","created":"2025-12-31","cited_by_count":23,"area":"alignment"},{"id":"2407.13709","title":"Understanding Reference Policies in Direct Preference Optimization","created":"2024-07-18","cited_by_count":22,"area":"alignment"},{"id":"2409.06957","title":"Policy Filtration for RLHF to Mitigate Noise in Reward Models","created":"2024-09-11","cited_by_count":22,"area":"alignment"},{"id":"2410.18640","title":"Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model","created":"2024-10-24","cited_by_count":22,"area":"alignment"},{"id":"2501.14940","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","created":"2025-01-24","cited_by_count":20,"area":"alignment"},{"id":"2410.14148","title":"Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment","created":"2024-10-18","cited_by_count":19,"area":"alignment"},{"id":"2501.12273","title":"Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement","created":"2025-01-21","cited_by_count":18,"area":"alignment"},{"id":"2409.02795","title":"Towards a Unified View of Preference Learning for Large Language Models: A Survey","created":"2024-09-04","cited_by_count":17,"area":"alignment"},{"id":"2410.18027","title":"Cross-lingual Transfer of Reward Models in Multilingual Alignment","created":"2024-10-23","cited_by_count":17,"area":"alignment"},{"id":"2506.03850","title":"Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning","created":"2025-06-04","cited_by_count":17,"area":"alignment"},{"id":"2507.00018","title":"Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections","created":"2025-06-15","cited_by_count":17,"area":"alignment"},{"id":"2502.04322","title":"Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions","created":"2025-02-06","cited_by_count":15,"area":"alignment"},{"id":"2505.20259","title":"Lifelong Safety Alignment for Language Models","created":"2025-05-26","cited_by_count":15,"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":"2410.05328","title":"Reward Learning From Preference With Ties","created":"2024-10-05","cited_by_count":14,"area":"alignment"},{"id":"2504.03784","title":"Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuning","created":"2025-04-03","cited_by_count":13,"area":"alignment"},{"id":"2412.01253","title":"Yi-Lightning Technical Report","created":"2024-12-02","cited_by_count":12,"area":"alignment"},{"id":"2412.15289","title":"SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage","created":"2024-12-19","cited_by_count":11,"area":"alignment"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2502.19731","title":"Preference Learning Unlocks LLMs' Psycho-Counseling Skills","created":"2025-02-27","cited_by_count":10,"area":"alignment"},{"id":"2409.06411","title":"Length Desensitization in Direct Preference Optimization","created":"2024-09-10","cited_by_count":8,"area":"alignment"},{"id":"2410.23223","title":"COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences","created":"2024-10-30","cited_by_count":8,"area":"alignment"},{"id":"2505.04993","title":"Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes","created":"2025-05-08","cited_by_count":7,"area":"alignment"},{"id":"2506.18245","title":"Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection","created":"2025-06-23","cited_by_count":7,"area":"alignment"},{"id":"2409.13948","title":"Aligning Language Models Using Follow-up Likelihood as Reward Signal","created":"2024-09-20","cited_by_count":6,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2502.01925","title":"PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling","created":"2025-02-04","cited_by_count":6,"area":"alignment"},{"id":"2409.08845","title":"AIPO: Improving Training Objective for Iterative Preference Optimization","created":"2024-09-13","cited_by_count":5,"area":"alignment"},{"id":"2411.02785","title":"Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment","created":"2024-11-05","cited_by_count":5,"area":"alignment"},{"id":"2502.13177","title":"KL Penalty Control via Perturbation for Direct Preference Optimization","created":"2025-02-18","cited_by_count":5,"area":"alignment"},{"id":"2505.23316","title":"Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO","created":"2025-05-29","cited_by_count":5,"area":"alignment"},{"id":"2506.04180","title":"SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models","created":"2025-06-04","cited_by_count":5,"area":"alignment"},{"id":"2512.17375","title":"AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens","created":"2025-12-19","cited_by_count":4,"area":"alignment"},{"id":"2501.14294","title":"Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes","created":"2025-01-24","cited_by_count":3,"area":"alignment"},{"id":"2509.23542","title":"On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2510.20449","title":"LM-mixup: Text Data Augmentation via Language Model based Mixup","created":"2025-10-23","cited_by_count":3,"area":"alignment"},{"id":"2601.19231","title":"LLMs Can Unlearn Refusal with Only 1,000 Benign Samples","created":"2026-01-27","cited_by_count":3,"area":"alignment"},{"id":"2504.06659","title":"Leveraging Machine Unlearning for Cost-Efficient Preference Alignment","created":"2025-04-09","cited_by_count":2,"area":"alignment"},{"id":"2511.10656","title":"Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models","created":"2025-11-03","cited_by_count":2,"area":"alignment"},{"id":"2603.12963","title":"Long-form RewardBench: Evaluating Reward Models for Long-form Generation","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2412.17572","title":"Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor","created":"2024-12-23","cited_by_count":1,"area":"alignment"},{"id":"2412.20996","title":"Plug-and-Play Training Framework for Preference Optimization","created":"2024-12-30","cited_by_count":1,"area":"alignment"},{"id":"2505.22092","title":"VIRAL: Vision-grounded Integration for Reward design And Learning","created":"2025-05-28","cited_by_count":1,"area":"alignment"},{"id":"2506.05260","title":"LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs","created":"2025-06-05","cited_by_count":1,"area":"alignment"},{"id":"2506.13702","title":"Value-Free Policy Optimization via Reward Partitioning","created":"2025-06-16","cited_by_count":1,"area":"alignment"},{"id":"2507.20181","title":"SGPO: Self-Generated Preference Optimization based on Self-Improver","created":"2025-07-27","cited_by_count":1,"area":"alignment"},{"id":"2508.14947","title":"Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization","created":"2025-08-20","cited_by_count":1,"area":"alignment"},{"id":"2510.02493","title":"Beyond Imitation: Recovering Dense Rewards from Demonstrations","created":"2025-10-02","cited_by_count":1,"area":"alignment"},{"id":"2510.19265","title":"Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2605.12667","title":"ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization","created":"2026-05-12","cited_by_count":1,"area":"alignment"},{"id":"2605.29396","title":"Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2502.12189","title":"Self-supervised Attribute-aware Dynamic Preference Ranking Alignment","created":"2025-02-15","cited_by_count":0,"area":"alignment"},{"id":"2503.04346","title":"Adding Alignment Control to Language Models","created":"2025-03-06","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":"2506.09096","title":"Intra-Trajectory Consistency for Reward Modeling","created":"2025-06-10","cited_by_count":0,"area":"alignment"},{"id":"2509.12221","title":"MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors","created":"2025-09-04","cited_by_count":0,"area":"alignment"},{"id":"2601.04262","title":"Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis","created":"2026-01-07","cited_by_count":0,"area":"alignment"},{"id":"2604.04410","title":"Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment","created":"2026-04-06","cited_by_count":0,"area":"alignment"},{"id":"2604.16378","title":"Reciprocal Co-Training (RCT): Coupling Gradient-Based and Non-Differentiable Models via Reinforcement Learning","created":"2026-03-24","cited_by_count":0,"area":"alignment"},{"id":"2605.04992","title":"You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation","created":"2026-05-06","cited_by_count":0,"area":"alignment"},{"id":"2605.07883","title":"Beyond \"I cannot fulfill this request\": Alleviating Rigid Rejection in LLMs via Label Enhancement","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.13537","title":"Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment","created":"2026-05-13","cited_by_count":0,"area":"alignment"},{"id":"2605.28722","title":"Multi-Adapter Representation Interventions via Energy Calibration","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2607.11475","title":"HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models","created":"2026-07-13","cited_by_count":0,"area":"alignment"},{"id":"2609.32617","title":"The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2609.33298","title":"Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2610.00715","title":"Robust Nash Alignment under Preference Uncertainty","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.06670","title":"Reward Stealing Attack on Large Language Models","created":"2026-10-05","cited_by_count":0,"area":"alignment"}],"next_cursor":null}