{"total":93,"rows":[{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472,"area":"alignment"},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297,"area":"alignment"},{"id":"2311.10702","title":"Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2","created":"2023-11-17","cited_by_count":229,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2410.16184","title":"RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style","created":"2024-10-21","cited_by_count":176,"area":"alignment"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2506.01937","title":"RewardBench 2: Advancing Reward Model Evaluation","created":"2025-06-02","cited_by_count":150,"area":"alignment"},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136,"area":"alignment"},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122,"area":"alignment"},{"id":"2402.05369","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","created":"2024-02-08","cited_by_count":85,"area":"alignment"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2310.06762","title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models","created":"2023-10-10","cited_by_count":66,"area":"alignment"},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2404.09656","title":"Learn Your Reference Model for Real Good Alignment","created":"2024-04-15","cited_by_count":57,"area":"alignment"},{"id":"2310.05910","title":"SALMON: Self-Alignment with Instructable Reward Models","created":"2023-10-09","cited_by_count":55,"area":"alignment"},{"id":"2406.14144","title":"Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons","created":"2024-06-20","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":"2408.06266","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment","created":"2024-08-12","cited_by_count":46,"area":"alignment"},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2508.03686","title":"CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward","created":"2025-08-05","cited_by_count":40,"area":"alignment"},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39,"area":"alignment"},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2503.11701","title":"A Survey of Direct Preference Optimization","created":"2025-03-12","cited_by_count":36,"area":"alignment"},{"id":"2307.12966","title":"Aligning Large Language Models with Human: A Survey","created":"2023-07-24","cited_by_count":32,"area":"alignment"},{"id":"2409.17407","title":"Post-hoc Reward Calibration: A Case Study on Length Bias","created":"2024-09-25","cited_by_count":29,"area":"alignment"},{"id":"2506.08123","title":"QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA","created":"2025-06-09","cited_by_count":28,"area":"alignment"},{"id":"2410.19133","title":"Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback","created":"2024-10-24","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":"2405.05008","title":"ADELIE: Aligning Large Language Models on Information Extraction","created":"2024-05-08","cited_by_count":24,"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":"2505.13388","title":"R3: Robust Rubric-Agnostic Reward Models","created":"2025-05-19","cited_by_count":23,"area":"alignment"},{"id":"2502.11555","title":"Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models","created":"2025-02-17","cited_by_count":22,"area":"alignment"},{"id":"2405.13432","title":"Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction","created":"2024-05-22","cited_by_count":18,"area":"alignment"},{"id":"2405.13820","title":"Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching","created":"2024-05-22","cited_by_count":17,"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":"2502.16182","title":"IPO: Your Language Model is Secretly a Preference Classifier","created":"2025-02-22","cited_by_count":17,"area":"alignment"},{"id":"2406.04879","title":"A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques","created":"2024-06-07","cited_by_count":16,"area":"alignment"},{"id":"2402.12219","title":"Reformatted Alignment","created":"2024-02-19","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":"2502.11026","title":"RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment","created":"2025-02-16","cited_by_count":14,"area":"alignment"},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13,"area":"alignment"},{"id":"2503.05079","title":"On a Connection Between Imitation Learning and RLHF","created":"2025-03-07","cited_by_count":13,"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":"2505.11166","title":"SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization","created":"2025-05-16","cited_by_count":10,"area":"alignment"},{"id":"2510.17426","title":"Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging","created":"2025-10-20","cited_by_count":10,"area":"alignment"},{"id":"2406.07168","title":"Teaching Language Models to Self-Improve by Learning from Language Feedback","created":"2024-06-11","cited_by_count":9,"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":"2505.12762","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","created":"2025-05-19","cited_by_count":8,"area":"alignment"},{"id":"2505.13878","title":"InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models","created":"2025-05-20","cited_by_count":8,"area":"alignment"},{"id":"2512.20806","title":"Safety Alignment of LMs via Non-cooperative Games","created":"2025-12-23","cited_by_count":8,"area":"alignment"},{"id":"2602.00038","title":"LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion","created":"2026-01-19","cited_by_count":8,"area":"alignment"},{"id":"2512.23461","title":"Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance","created":"2025-12-29","cited_by_count":7,"area":"alignment"},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2501.01336","title":"Aligning Large Language Models for Faithful Integrity Against Opposing Argument","created":"2025-01-02","cited_by_count":6,"area":"alignment"},{"id":"2504.14452","title":"ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data","created":"2025-04-20","cited_by_count":6,"area":"alignment"},{"id":"2505.07558","title":"Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models","created":"2025-05-12","cited_by_count":6,"area":"alignment"},{"id":"2508.16100","title":"CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency","created":"2025-08-22","cited_by_count":6,"area":"alignment"},{"id":"2510.10963","title":"APLOT: Robust Reward Modeling via Adaptive Preference Learning with Optimal Transport","created":"2025-10-13","cited_by_count":6,"area":"alignment"},{"id":"2407.02119","title":"Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning","created":"2024-07-02","cited_by_count":5,"area":"alignment"},{"id":"2502.03397","title":"SPRI: Aligning Large Language Models with Context-Situated Principles","created":"2025-02-05","cited_by_count":5,"area":"alignment"},{"id":"2602.10623","title":"Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling","created":"2026-02-11","cited_by_count":5,"area":"alignment"},{"id":"2404.18410","title":"Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting","created":"2024-04-29","cited_by_count":4,"area":"alignment"},{"id":"2406.19071","title":"EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization","created":"2024-06-27","cited_by_count":4,"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":"2509.17276","title":"Probabilistic Token Alignment for Large Language Model Fusion","created":"2025-09-21","cited_by_count":3,"area":"alignment"},{"id":"2510.07118","title":"TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning","created":"2025-10-08","cited_by_count":3,"area":"alignment"},{"id":"2510.18081","title":"Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth","created":"2025-10-20","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":"2608.06377","title":"Learning When to Trust via Selective Context Preference Optimization","created":"2026-08-06","cited_by_count":3,"area":"alignment"},{"id":"2411.00809","title":"Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment","created":"2024-10-23","cited_by_count":2,"area":"alignment"},{"id":"2504.08590","title":"Playpen: An Environment for Exploring Learning Through Conversational Interaction","created":"2025-04-11","cited_by_count":2,"area":"alignment"},{"id":"2506.02479","title":"BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2511.09385","title":"AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment","created":"2025-11-12","cited_by_count":2,"area":"alignment"},{"id":"2511.09864","title":"Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models","created":"2025-11-13","cited_by_count":2,"area":"alignment"},{"id":"2602.13551","title":"Small Reward Models via Backward Inference","created":"2026-02-14","cited_by_count":2,"area":"alignment"},{"id":"2603.19311","title":"PrefPO: Pairwise Preference Prompt Optimization","created":"2026-03-13","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":"2511.10985","title":"When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets","created":"2025-11-14","cited_by_count":1,"area":"alignment"},{"id":"2604.00979","title":"Dual Optimal: Make Your LLM Peer-like with Dignity","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2505.10775","title":"A Systematic Analysis of Base Model Choice for Reward Modeling","created":"2025-05-16","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":"2506.02018","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","created":"2025-05-28","cited_by_count":0,"area":"alignment"},{"id":"2509.24781","title":"SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models","created":"2025-09-29","cited_by_count":0,"area":"alignment"},{"id":"2511.12867","title":"Bootstrapping LLMs via Preference-Based Policy Optimization","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2602.02898","title":"Aligning Language Model Benchmarks with Pairwise Preferences","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2603.04429","title":"What Is Missing: Interpretable Ratings for Large Language Model Outputs","created":"2026-02-17","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":"2607.02914","title":"Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2610.01511","title":"GAW-PO: Preference Optimization with Gradient-Aligned Token Weights","created":"2026-10-01","cited_by_count":0,"area":"alignment"},{"id":"2610.04328","title":"Bidirectional Preference Synthesis: Learning Prompt-Conditioned Preferences from Boundary Failures","created":"2026-10-03","cited_by_count":0,"area":"alignment"},{"id":"2610.20350","title":"Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}