{"total":95,"rows":[{"id":"2407.07880","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","created":"2024-07-10","cited_by_count":53,"area":"alignment"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2412.14516","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","created":"2024-12-19","cited_by_count":51,"area":"alignment"},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"},{"id":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"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":"2410.04203","title":"RainbowPO: A Unified Framework for Combining Improvements in Preference Optimization","created":"2024-10-05","cited_by_count":19,"area":"alignment"},{"id":"2409.06691","title":"Geometric-Averaged Preference Optimization for Soft Preference Labels","created":"2024-09-10","cited_by_count":18,"area":"alignment"},{"id":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2404.04102","title":"ROPO: Robust Preference Optimization for Large Language Models","created":"2024-04-05","cited_by_count":16,"area":"alignment"},{"id":"2410.05328","title":"Reward Learning From Preference With Ties","created":"2024-10-05","cited_by_count":14,"area":"alignment"},{"id":"2407.18676","title":"Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift","created":"2024-07-26","cited_by_count":13,"area":"alignment"},{"id":"2412.02685","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","created":"2024-12-03","cited_by_count":13,"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":"2506.03690","title":"Robust Preference Optimization via Dynamic Target Margins","created":"2025-06-04","cited_by_count":13,"area":"alignment"},{"id":"2503.00539","title":"Distributionally Robust Reinforcement Learning with Human Feedback","created":"2025-03-01","cited_by_count":12,"area":"alignment"},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2408.09385","title":"Reward Difference Optimization For Sample Reweighting In Offline RLHF","created":"2024-08-18","cited_by_count":10,"area":"alignment"},{"id":"2502.18099","title":"Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment","created":"2025-02-25","cited_by_count":10,"area":"alignment"},{"id":"2405.00747","title":"Soft Preference Optimization: Aligning Language Models to Expert Distributions","created":"2024-04-30","cited_by_count":9,"area":"alignment"},{"id":"2410.11055","title":"Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only","created":"2024-10-14","cited_by_count":9,"area":"alignment"},{"id":"2505.15694","title":"A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO","created":"2025-05-21","cited_by_count":8,"area":"alignment"},{"id":"2408.03459","title":"Can DPO Learn Diverse Human Values? A Theoretical Scaling Law","created":"2024-08-06","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":"2504.10208","title":"From Prompting to Alignment: A Generative Framework for Query Recommendation","created":"2025-04-14","cited_by_count":7,"area":"alignment"},{"id":"2505.18720","title":"Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization","created":"2025-05-24","cited_by_count":7,"area":"alignment"},{"id":"2603.18736","title":"CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks","created":"2026-03-19","cited_by_count":7,"area":"alignment"},{"id":"2502.20847","title":"Gradient Imbalance in Direct Preference Optimization","created":"2025-02-28","cited_by_count":6,"area":"alignment"},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2409.07772","title":"Alignment with Preference Optimization Is All You Need for LLM Safety","created":"2024-09-12","cited_by_count":5,"area":"alignment"},{"id":"2410.01957","title":"Challenges and Future Directions of Data-Centric AI Alignment","created":"2024-10-02","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":"2410.09362","title":"SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins","created":"2024-10-12","cited_by_count":5,"area":"alignment"},{"id":"2411.03700","title":"The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models","created":"2024-11-06","cited_by_count":5,"area":"alignment"},{"id":"2501.07886","title":"Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision","created":"2025-01-14","cited_by_count":5,"area":"alignment"},{"id":"2512.23816","title":"Improved Bounds for Private and Robust Alignment","created":"2025-12-29","cited_by_count":5,"area":"alignment"},{"id":"2605.11134","title":"Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training","created":"2026-05-11","cited_by_count":5,"area":"alignment"},{"id":"2503.07426","title":"RePO: Understanding Preference Learning Through ReLU-Based Optimization","created":"2025-03-10","cited_by_count":4,"area":"alignment"},{"id":"2503.10093","title":"Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling","created":"2025-03-13","cited_by_count":4,"area":"alignment"},{"id":"2504.16628","title":"ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data","created":"2025-04-23","cited_by_count":4,"area":"alignment"},{"id":"2505.17859","title":"Scalable Valuation of Human Feedback through Provably Robust Model Alignment","created":"2025-05-23","cited_by_count":4,"area":"alignment"},{"id":"2505.24709","title":"On Symmetric Losses for Robust Policy Optimization with Noisy Preferences","created":"2025-05-30","cited_by_count":4,"area":"alignment"},{"id":"2602.07340","title":"Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control","created":"2026-02-07","cited_by_count":4,"area":"alignment"},{"id":"2408.12799","title":"Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora","created":"2024-08-23","cited_by_count":3,"area":"alignment"},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","cited_by_count":3,"area":"alignment"},{"id":"2510.01458","title":"How Well Can Preference Optimization Generalize Under Noisy Feedback?","created":"2025-10-01","cited_by_count":3,"area":"alignment"},{"id":"2605.02971","title":"Multilingual Safety Alignment via Self-Distillation","created":"2026-05-03","cited_by_count":3,"area":"alignment"},{"id":"2503.10228","title":"Policy Teaching via Data Poisoning in Learning from Human Preferences","created":"2025-03-13","cited_by_count":2,"area":"alignment"},{"id":"2503.12301","title":"One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise","created":"2025-03-16","cited_by_count":2,"area":"alignment"},{"id":"2504.05831","title":"Leveraging Robust Optimization for LLM Alignment under Distribution Shifts","created":"2025-04-08","cited_by_count":2,"area":"alignment"},{"id":"2509.10515","title":"Adaptive Preference Optimization with Uncertainty-aware Utility Anchor","created":"2025-09-03","cited_by_count":2,"area":"alignment"},{"id":"2509.19104","title":"Online Distributionally Robust LLM Alignment via Regression to Relative Reward","created":"2025-09-23","cited_by_count":2,"area":"alignment"},{"id":"2509.23564","title":"Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment","created":"2025-09-28","cited_by_count":2,"area":"alignment"},{"id":"2509.24159","title":"RE-PO: Robust Enhanced Policy Optimization as a General Framework for LLM Alignment","created":"2025-09-29","cited_by_count":2,"area":"alignment"},{"id":"2510.18713","title":"Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options","created":"2025-10-21","cited_by_count":2,"area":"alignment"},{"id":"2510.23590","title":"Lightweight Robust Direct Preference Optimization","created":"2025-10-27","cited_by_count":2,"area":"alignment"},{"id":"2602.00954","title":"Small-Margin Preferences Still Matter-If You Train Them Right","created":"2026-02-01","cited_by_count":2,"area":"alignment"},{"id":"2604.18239","title":"Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner","created":"2026-04-20","cited_by_count":2,"area":"alignment"},{"id":"2503.01233","title":"PEO: Improving Bi-Factorial Preference Alignment with Post-Training Policy Extrapolation","created":"2025-03-03","cited_by_count":1,"area":"alignment"},{"id":"2508.06783","title":"PROPS: Progressively Private Self-alignment of Large Language Models","created":"2025-08-09","cited_by_count":1,"area":"alignment"},{"id":"2510.04087","title":"Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling","created":"2025-10-05","cited_by_count":1,"area":"alignment"},{"id":"2510.05342","title":"Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization","created":"2025-10-06","cited_by_count":1,"area":"alignment"},{"id":"2512.23693","title":"Fine-Tuning LLMs with Fine-Grained Human Feedback on Text Spans","created":"2025-12-29","cited_by_count":1,"area":"alignment"},{"id":"2602.11902","title":"Mitigating Mismatch within Reference-based Preference Optimization","created":"2026-02-12","cited_by_count":1,"area":"alignment"},{"id":"2603.07211","title":"CompassDPO: Dynamics-Controlled Direct Preference Optimization for Robust Safety Alignment","created":"2026-03-07","cited_by_count":1,"area":"alignment"},{"id":"2603.20453","title":"Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2605.02495","title":"Efficient Preference Poisoning Attack on Offline RLHF","created":"2026-05-04","cited_by_count":1,"area":"alignment"},{"id":"2605.06987","title":"Response Time Enhances Alignment with Heterogeneous Preferences","created":"2026-05-07","cited_by_count":1,"area":"alignment"},{"id":"2607.16240","title":"Normalized Rewards for Preference Optimization","created":"2026-06-26","cited_by_count":1,"area":"alignment"},{"id":"2403.02745","title":"CURATRON: Complete and Robust Preference Data for Rigorous Alignment of Large Language Models","created":"2024-03-05","cited_by_count":0,"area":"alignment"},{"id":"2405.15230","title":"$i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization","created":"2024-05-24","cited_by_count":0,"area":"alignment"},{"id":"2505.01706","title":"Inducing Robustness in a 2 Dimensional Direct Preference Optimization Paradigm","created":"2025-05-03","cited_by_count":0,"area":"alignment"},{"id":"2505.19134","title":"Incentivizing High-Quality Human Annotations with Golden Questions","created":"2025-05-25","cited_by_count":0,"area":"alignment"},{"id":"2508.09653","title":"On Negative-aware Preference Optimization for Recommendation","created":"2025-08-13","cited_by_count":0,"area":"alignment"},{"id":"2510.13830","title":"Users as Annotators: LLM Preference Learning from Comparison Mode","created":"2025-10-10","cited_by_count":0,"area":"alignment"},{"id":"2511.02623","title":"The Realignment Problem: When Right becomes Wrong in LLMs","created":"2025-11-04","cited_by_count":0,"area":"alignment"},{"id":"2602.04909","title":"Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment","created":"2026-02-04","cited_by_count":0,"area":"alignment"},{"id":"2603.04968","title":"When Weak LLMs Speak with Confidence, Preference Alignment Gets Stronger","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2603.08145","title":"DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2603.08412","title":"Aligning to Illusions: Choice Blindness in Human and AI Feedback","created":"2026-03-09","cited_by_count":0,"area":"alignment"},{"id":"2606.19607","title":"Which Pairs to Compare for LLM Post-Training?","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2606.20482","title":"Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users","created":"2026-06-18","cited_by_count":0,"area":"alignment"},{"id":"2607.01715","title":"Distributionally Robust Listwise Preference Optimization","created":"2026-07-02","cited_by_count":0,"area":"alignment"},{"id":"2607.03248","title":"Unbiased Alignment for Large Language Models with Noisy Preferences","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2607.09796","title":"Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels","created":"2026-07-09","cited_by_count":0,"area":"alignment"},{"id":"2607.20515","title":"Reliability-Aware LLM Alignment from Inconsistent Human Feedback","created":"2026-07-07","cited_by_count":0,"area":"alignment"},{"id":"2608.27032","title":"Disentangling Optimization Scale from Preference Scale in DPO","created":"2026-08-27","cited_by_count":0,"area":"alignment"},{"id":"2608.30597","title":"PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.06893","title":"Towards Bridging the Gap Between Offline and Iterative Alignment via Preference Distillation","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2609.12607","title":"Direct Preference Density Alignment for Conversational Audio Equalization","created":"2026-09-11","cited_by_count":0,"area":"alignment"},{"id":"2609.16532","title":"Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data","created":"2026-09-15","cited_by_count":0,"area":"alignment"},{"id":"2609.34374","title":"ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.13066","title":"Evolving Creatives with Clicks: CTR-Driven Advertising image Editing via Attribute Disentanglement and Preference Alignment","created":"2026-10-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}