{"total":67,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748,"area":"alignment"},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571,"area":"alignment"},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318,"area":"alignment"},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315,"area":"alignment"},{"id":"2405.20947","title":"OR-Bench: An Over-Refusal Benchmark for Large Language Models","created":"2024-05-31","cited_by_count":244,"area":"alignment"},{"id":"2503.05236","title":"Unified Reward Model for Multimodal Understanding and Generation","created":"2025-03-07","cited_by_count":199,"area":"alignment"},{"id":"2402.11411","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","created":"2024-02-18","cited_by_count":198,"area":"alignment"},{"id":"2405.17220","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","created":"2024-05-27","cited_by_count":131,"area":"alignment"},{"id":"2509.26346","title":"EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing","created":"2025-09-30","cited_by_count":62,"area":"alignment"},{"id":"2402.18091","title":"Polos: Multimodal Metric Learning from Human Feedback for Image Captioning","created":"2024-02-28","cited_by_count":46,"area":"alignment"},{"id":"2405.19335","title":"X-VILA: Cross-Modality Alignment for Large Language Model","created":"2024-05-29","cited_by_count":46,"area":"alignment"},{"id":"2503.20823","title":"Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy","created":"2025-03-26","cited_by_count":44,"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":"2410.18013","title":"Scalable Ranked Preference Optimization for Text-to-Image Generation","created":"2024-10-23","cited_by_count":33,"area":"alignment"},{"id":"2509.23738","title":"GUI-Shepherd: Reliable Process Reward and Verification for Long-Sequence GUI Tasks","created":"2025-09-28","cited_by_count":26,"area":"alignment"},{"id":"2506.14175","title":"GRAM: A Generative Foundation Reward Model for Reward Generalization","created":"2025-06-17","cited_by_count":25,"area":"alignment"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2506.02095","title":"Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences","created":"2025-06-02","cited_by_count":22,"area":"alignment"},{"id":"2403.04204","title":"On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models","created":"2024-03-07","cited_by_count":21,"area":"alignment"},{"id":"2406.13173","title":"Biomedical Visual Instruction Tuning with Clinician Preference Alignment","created":"2024-06-19","cited_by_count":21,"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":"2406.10522","title":"Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning","created":"2024-06-15","cited_by_count":19,"area":"alignment"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2504.13122","title":"VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models","created":"2025-04-17","cited_by_count":17,"area":"alignment"},{"id":"2506.17252","title":"Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization","created":"2025-06-08","cited_by_count":17,"area":"alignment"},{"id":"2405.20216","title":"Boost Your Human Image Generation Model via Direct Preference Optimization","created":"2024-05-30","cited_by_count":16,"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":"2501.04561","title":"OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis","created":"2025-01-08","cited_by_count":10,"area":"alignment"},{"id":"2406.01514","title":"Decoupled Alignment for Robust Plug-and-Play Adaptation","created":"2024-06-03","cited_by_count":9,"area":"alignment"},{"id":"2509.00723","title":"OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination","created":"2025-08-31","cited_by_count":9,"area":"alignment"},{"id":"2504.14096","title":"VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment","created":"2025-04-18","cited_by_count":8,"area":"alignment"},{"id":"2602.21655","title":"CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning","created":"2026-02-25","cited_by_count":8,"area":"alignment"},{"id":"2402.10896","title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter","created":"2024-02-16","cited_by_count":7,"area":"alignment"},{"id":"2409.04183","title":"GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding","created":"2024-09-06","cited_by_count":7,"area":"alignment"},{"id":"2412.00624","title":"VideoSAVi: Self-Aligned Video Language Models without Human Supervision","created":"2024-12-01","cited_by_count":7,"area":"alignment"},{"id":"2504.12083","title":"Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization","created":"2025-04-16","cited_by_count":7,"area":"alignment"},{"id":"2409.20053","title":"GUNDAM: Aligning Large Language Models with Graph Understanding","created":"2024-09-30","cited_by_count":5,"area":"alignment"},{"id":"2505.17910","title":"DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning","created":"2025-05-23","cited_by_count":5,"area":"alignment"},{"id":"2510.17833","title":"Brain-Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage","created":"2025-10-03","cited_by_count":5,"area":"alignment"},{"id":"2602.02033","title":"One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation","created":"2026-02-02","cited_by_count":5,"area":"alignment"},{"id":"2603.15117","title":"MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge","created":"2026-03-16","cited_by_count":5,"area":"alignment"},{"id":"2603.25108","title":"MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning","created":"2026-03-26","cited_by_count":5,"area":"alignment"},{"id":"2505.23950","title":"InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback","created":"2025-05-29","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":"2406.09397","title":"Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms","created":"2024-06-13","cited_by_count":3,"area":"alignment"},{"id":"2506.00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning","created":"2025-06-01","cited_by_count":3,"area":"alignment"},{"id":"2501.00039","title":"Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement Learning","created":"2024-12-25","cited_by_count":2,"area":"alignment"},{"id":"2509.17116","title":"MCTS-EP: Empowering Embodied Planning with Online Preference Optimization","created":"2025-09-21","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":"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":"2509.21351","title":"Random Direct Preference Optimization for Radiography Report Generation","created":"2025-09-19","cited_by_count":1,"area":"alignment"},{"id":"2607.29025","title":"Evaluation-Verification Reward for Consistent Multi-Reference Image Editing","created":"2026-07-31","cited_by_count":1,"area":"alignment"},{"id":"2406.13357","title":"Transferable speech-to-text large language model alignment module","created":"2024-06-19","cited_by_count":0,"area":"alignment"},{"id":"2502.03512","title":"YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment","created":"2025-02-05","cited_by_count":0,"area":"alignment"},{"id":"2510.02561","title":"Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback","created":"2025-10-02","cited_by_count":0,"area":"alignment"},{"id":"2602.13055","title":"Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation","created":"2026-02-13","cited_by_count":0,"area":"alignment"},{"id":"2603.01784","title":"Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution","created":"2026-03-02","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":"2606.14586","title":"S$^2$COPE: Self-Supervised Concept Discovery via Preference Learning","created":"2026-06-12","cited_by_count":0,"area":"alignment"},{"id":"2608.08491","title":"TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models","created":"2026-08-09","cited_by_count":0,"area":"alignment"},{"id":"2609.00879","title":"Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.33640","title":"SafeMol: Dual-Modality Safety Alignment for Molecular Multimodal Models","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.34033","title":"Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.39688","title":"ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models","created":"2026-09-30","cited_by_count":0,"area":"alignment"}],"next_cursor":null}