{"total":44,"rows":[{"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":"2309.06256","title":"Mitigating the Alignment Tax of RLHF","created":"2023-09-12","cited_by_count":183,"area":"alignment"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2403.17141","title":"MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models","created":"2024-03-25","cited_by_count":44,"area":"alignment"},{"id":"2404.16792","title":"Model Extrapolation Expedites Alignment","created":"2024-04-25","cited_by_count":37,"area":"alignment"},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"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":"2402.03749","title":"Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models","created":"2024-02-06","cited_by_count":28,"area":"alignment"},{"id":"2407.08770","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","created":"2024-07-11","cited_by_count":23,"area":"alignment"},{"id":"2405.19988","title":"Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics","created":"2024-05-30","cited_by_count":19,"area":"alignment"},{"id":"2210.07792","title":"Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning","created":"2022-10-14","cited_by_count":14,"area":"alignment"},{"id":"2302.00270","title":"Internally Rewarded Reinforcement Learning","created":"2023-02-01","cited_by_count":14,"area":"alignment"},{"id":"2310.03013","title":"SemiReward: A General Reward Model for Semi-supervised Learning","created":"2023-10-04","cited_by_count":14,"area":"alignment"},{"id":"2310.07932","title":"What Matters to You? Towards Visual Representation Alignment for Robot Learning","created":"2023-10-11","cited_by_count":14,"area":"alignment"},{"id":"2205.15367","title":"Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning","created":"2022-05-30","cited_by_count":13,"area":"alignment"},{"id":"2503.01076","title":"Active Learning for Direct Preference Optimization","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2504.07091","title":"AssistanceZero: Scalably Solving Assistance Games","created":"2025-04-09","cited_by_count":10,"area":"alignment"},{"id":"2506.12323","title":"Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback","created":"2025-06-14","cited_by_count":9,"area":"alignment"},{"id":"2308.11171","title":"ViCo: Engaging Video Comment Generation with Human Preference Rewards","created":"2023-08-22","cited_by_count":8,"area":"alignment"},{"id":"2411.02470","title":"Benchmarking XAI Explanations with Human-Aligned Evaluations","created":"2024-11-04","cited_by_count":8,"area":"alignment"},{"id":"2504.18026","title":"Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization","created":"2025-04-25","cited_by_count":7,"area":"alignment"},{"id":"2505.12843","title":"Bias Fitting to Mitigate Length Bias of Reward Model in RLHF","created":"2025-05-19","cited_by_count":7,"area":"alignment"},{"id":"2201.08102","title":"Safe Deep RL in 3D Environments using Human Feedback","created":"2022-01-20","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":"2510.08075","title":"Multi-Condition Conformal Selection","created":"2025-10-09","cited_by_count":4,"area":"alignment"},{"id":"1809.08714","title":"Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback","created":"2018-09-24","cited_by_count":3,"area":"alignment"},{"id":"2601.07449","title":"RLPO: Residual Listwise Preference Optimization for Long-Context Review Ranking","created":"2026-01-12","cited_by_count":3,"area":"alignment"},{"id":"2403.06735","title":"Enhancing Image Caption Generation Using Reinforcement Learning with Human Feedback","created":"2024-03-11","cited_by_count":2,"area":"alignment"},{"id":"2509.20938","title":"Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy Refinement","created":"2025-09-25","cited_by_count":2,"area":"alignment"},{"id":"1909.03622","title":"Transfer Reward Learning for Policy Gradient-Based Text Generation","created":"2019-09-09","cited_by_count":1,"area":"alignment"},{"id":"2409.13919","title":"Measuring Error Alignment for Decision-Making Systems","created":"2024-09-20","cited_by_count":1,"area":"alignment"},{"id":"2501.15219","title":"Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction","created":"2025-01-25","cited_by_count":1,"area":"alignment"},{"id":"2505.12322","title":"Model alignment using inter-modal bridges","created":"2025-05-18","cited_by_count":1,"area":"alignment"},{"id":"2510.19562","title":"DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2603.00159","title":"FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation","created":"2026-02-25","cited_by_count":1,"area":"alignment"},{"id":"2603.03280","title":"How to Peel with a Knife: Aligning Fine-Grained Manipulation with Human Preference","created":"2026-03-03","cited_by_count":1,"area":"alignment"},{"id":"2606.31377","title":"Stage-Transition Dense Reward Modeling for Reinforcement Learning","created":"2026-06-30","cited_by_count":1,"area":"alignment"},{"id":"2408.10844","title":"Aligning Object Detector Bounding Boxes with Human Preference","created":"2024-08-20","cited_by_count":0,"area":"alignment"},{"id":"2604.03417","title":"Beauty in the Eye of AI: Aligning LLMs and Vision Models with Human Aesthetics in Network Visualization","created":"2026-04-03","cited_by_count":0,"area":"alignment"},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.05028","title":"Compositional Reward Models for Conditional Medical Image Generation","created":"2026-09-04","cited_by_count":0,"area":"alignment"},{"id":"2609.09793","title":"How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE","created":"2026-09-09","cited_by_count":0,"area":"alignment"},{"id":"2609.34506","title":"Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarks","created":"2026-09-28","cited_by_count":0,"area":"alignment"}],"next_cursor":null}