{"total":81,"rows":[{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"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":"2504.12501","title":"Reinforcement Learning from Human Feedback","created":"2025-04-16","cited_by_count":58,"area":"alignment"},{"id":"2503.15463","title":"From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment","created":"2025-03-19","cited_by_count":30,"area":"alignment"},{"id":"2501.12735","title":"Online Preference Alignment for Language Models via Count-based Exploration","created":"2025-01-22","cited_by_count":26,"area":"alignment"},{"id":"2502.00883","title":"SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters","created":"2025-02-02","cited_by_count":25,"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":"2412.06000","title":"Does RLHF Scale? Exploring the Impacts From Data, Model, and Method","created":"2024-12-08","cited_by_count":23,"area":"alignment"},{"id":"2502.04270","title":"PILAF: Optimal Human Preference Sampling for Reward Modeling","created":"2025-02-06","cited_by_count":20,"area":"alignment"},{"id":"2506.16507","title":"Robust Reward Modeling via Causal Rubrics","created":"2025-06-19","cited_by_count":19,"area":"alignment"},{"id":"2501.08617","title":"RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation","created":"2025-01-15","cited_by_count":15,"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":"2412.02685","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","created":"2024-12-03","cited_by_count":13,"area":"alignment"},{"id":"2409.06411","title":"Length Desensitization in Direct Preference Optimization","created":"2024-09-10","cited_by_count":8,"area":"alignment"},{"id":"2502.03095","title":"Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms","created":"2025-02-05","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":"2408.07471","title":"Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization","created":"2024-08-14","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":"2509.23102","title":"Multiplayer Nash Preference Optimization","created":"2025-09-27","cited_by_count":7,"area":"alignment"},{"id":"2502.00657","title":"LLM Safety Alignment is Divergence Estimation in Disguise","created":"2025-02-02","cited_by_count":6,"area":"alignment"},{"id":"2502.14619","title":"Reward Models Identify Consistency, Not Causality","created":"2025-02-20","cited_by_count":6,"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":"2501.13264","title":"OpenGenAlign: A Preference Dataset and Benchmark for Trustworthy Reward Modeling in Open-Ended, Long-Context Generation","created":"2025-01-22","cited_by_count":5,"area":"alignment"},{"id":"2504.07856","title":"Dual-Difficulty Curriculum Learning for Direct Preference Optimization","created":"2025-04-10","cited_by_count":5,"area":"alignment"},{"id":"2510.08646","title":"Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy","created":"2025-10-09","cited_by_count":5,"area":"alignment"},{"id":"2406.15193","title":"Inference Time Alignment with Reward-Guided Tree Search","created":"2024-06-21","cited_by_count":4,"area":"alignment"},{"id":"2502.11284","title":"Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning","created":"2025-02-16","cited_by_count":4,"area":"alignment"},{"id":"2502.14560","title":"Less is More: Improving LLM Alignment via Preference Data Selection","created":"2025-02-20","cited_by_count":4,"area":"alignment"},{"id":"2510.13434","title":"$M^2PO$: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"id":"2502.02153","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","created":"2025-02-04","cited_by_count":3,"area":"alignment"},{"id":"2505.21907","title":"Modeling and Optimizing User Preferences in AI Copilots: A Comprehensive Survey and Taxonomy","created":"2025-05-28","cited_by_count":3,"area":"alignment"},{"id":"2602.10286","title":"What Does Preference Learning Recover from Pairwise Comparison Data?","created":"2026-02-10","cited_by_count":3,"area":"alignment"},{"id":"2604.12710","title":"LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety","created":"2026-04-13","cited_by_count":3,"area":"alignment"},{"id":"2608.06377","title":"Learning When to Trust via Selective Context Preference Optimization","created":"2026-08-06","cited_by_count":3,"area":"alignment"},{"id":"2608.27505","title":"A Survey on Rubric-Guided Reinforcement Learning for Language Models","created":"2026-08-27","cited_by_count":3,"area":"alignment"},{"id":"2502.02628","title":"e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design Exploration","created":"2025-02-04","cited_by_count":2,"area":"alignment"},{"id":"2512.21917","title":"Semiparametric Preference Optimization: Your Language Model is Secretly a Single-Index Model","created":"2025-12-26","cited_by_count":2,"area":"alignment"},{"id":"2601.05882","title":"An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift","created":"2026-01-09","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":"2606.16276","title":"SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data","created":"2026-06-15","cited_by_count":2,"area":"alignment"},{"id":"2608.02109","title":"Same Semantics, Different Paths: Self-Improving Alignment for Vision-Text Compression","created":"2026-08-03","cited_by_count":2,"area":"alignment"},{"id":"2608.31079","title":"Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization","created":"2026-08-31","cited_by_count":2,"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":"2604.11121","title":"BITS Pilani at SemEval-2026 Task 9: Structured Supervised Fine-Tuning with DPO Refinement for Polarization Detection","created":"2026-04-13","cited_by_count":1,"area":"alignment"},{"id":"2605.02626","title":"Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models","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":"2607.07023","title":"Online Data Selection Is Implicit Alignment","created":"2026-07-08","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":"2608.27161","title":"STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation","created":"2026-08-27","cited_by_count":1,"area":"alignment"},{"id":"2609.12651","title":"Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner","created":"2026-09-11","cited_by_count":1,"area":"alignment"},{"id":"2412.07429","title":"Optimizing Alignment with Less: Leveraging Data Augmentation for Personalized Evaluation","created":"2024-12-10","cited_by_count":0,"area":"alignment"},{"id":"2502.04567","title":"Preference Optimization via Contrastive Divergence: Your Reward Model is Secretly an NLL Estimator","created":"2025-02-06","cited_by_count":0,"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":"2510.05534","title":"Revisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty","created":"2025-10-07","cited_by_count":0,"area":"alignment"},{"id":"2512.05518","title":"Matching Ranks Over Probability Yields Truly Deep Safety Alignment","created":"2025-12-05","cited_by_count":0,"area":"alignment"},{"id":"2601.06157","title":"ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment","created":"2026-01-06","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":"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":"2605.10863","title":"DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization","created":"2026-05-11","cited_by_count":0,"area":"alignment"},{"id":"2605.16345","title":"Goal-Conditioned Supervised Learning for LLM Fine-Tuning","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2606.28998","title":"Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation","created":"2026-06-27","cited_by_count":0,"area":"alignment"},{"id":"2607.13315","title":"Meta-Learning Preferences for Multilingual LLM Alignment","created":"2026-07-14","cited_by_count":0,"area":"alignment"},{"id":"2608.09568","title":"Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.09605","title":"TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation","created":"2026-08-10","cited_by_count":0,"area":"alignment"},{"id":"2608.12330","title":"Reliability-Aware Sexism Detection: Combining DPO with Annotator Agreement and Token-Level Confidence Scoring","created":"2026-06-01","cited_by_count":0,"area":"alignment"},{"id":"2608.15530","title":"Why Summaries Turn Neutral: Policy Attribution for Sentiment Drift in Reinforcement Learning from Human Feedback","created":"2026-08-16","cited_by_count":0,"area":"alignment"},{"id":"2608.24534","title":"Neurosymbolic Alignment for Physiologically-Safe Clinical Language Models","created":"2026-08-25","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":"2608.30902","title":"Low-Resource Preference Adaptation of LLMs via Activation-Based Label Propagation","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.01597","title":"The Rise of Verbal Reinforcement Learning","created":"2026-09-01","cited_by_count":0,"area":"alignment"},{"id":"2609.02273","title":"CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging","created":"2026-09-02","cited_by_count":0,"area":"alignment"},{"id":"2609.05899","title":"AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection","created":"2026-09-05","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":"2609.16340","title":"StalePO: Anchored Token-Level Preference Optimization using Legacy Post-Edits in Machine Translation","created":"2026-09-14","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":"2609.32617","title":"The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models","created":"2026-09-26","cited_by_count":0,"area":"alignment"},{"id":"2609.34374","title":"ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control","created":"2026-09-28","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":"2610.01323","title":"TRACE: Trajectory Return Attribution and Contrastive Erasure for Multi-Turn Safety","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.18415","title":"Do Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison","created":"2026-10-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}