{"total":111,"rows":[{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720,"area":"alignment"},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055,"area":"alignment"},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836,"area":"alignment"},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625,"area":"alignment"},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463,"area":"alignment"},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328,"area":"alignment"},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"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":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"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":"2006.13198","title":"Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks","created":"2020-06-23","cited_by_count":166,"area":"alignment"},{"id":"2406.02900","title":"Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms","created":"2024-06-05","cited_by_count":143,"area":"alignment"},{"id":"2406.10216","title":"Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs","created":"2024-06-14","cited_by_count":142,"area":"alignment"},{"id":"2310.05344","title":"SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF","created":"2023-10-09","cited_by_count":111,"area":"alignment"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"area":"alignment"},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79,"area":"alignment"},{"id":"2310.05199","title":"Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback","created":"2023-10-08","cited_by_count":78,"area":"alignment"},{"id":"2409.03444","title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities","created":"2024-09-05","cited_by_count":69,"area":"alignment"},{"id":"2501.19309","title":"Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment","created":"2025-01-31","cited_by_count":59,"area":"alignment"},{"id":"2505.00047","title":"Base Models Beat Aligned Models at Randomness and Creativity","created":"2025-04-30","cited_by_count":51,"area":"alignment"},{"id":"2405.20495","title":"Transfer Q Star: Principled Decoding for LLM Alignment","created":"2024-05-30","cited_by_count":48,"area":"alignment"},{"id":"2403.19270","title":"sDPO: Don't Use Your Data All at Once","created":"2024-03-28","cited_by_count":46,"area":"alignment"},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2409.13221","title":"Optimizing RLHF Training for Large Language Models with Stage Fusion","created":"2024-09-20","cited_by_count":43,"area":"alignment"},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2211.11602","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","created":"2022-11-21","cited_by_count":26,"area":"alignment"},{"id":"2403.11124","title":"Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment","created":"2024-03-17","cited_by_count":26,"area":"alignment"},{"id":"2503.22230","title":"Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback","created":"2025-03-28","cited_by_count":26,"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":"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":"2406.19774","title":"Direct Preference Knowledge Distillation for Large Language Models","created":"2024-06-28","cited_by_count":21,"area":"alignment"},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"id":"2410.06554","title":"The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models","created":"2024-10-09","cited_by_count":19,"area":"alignment"},{"id":"2408.11296","title":"RePair: Automated Program Repair with Process-based Feedback","created":"2024-08-21","cited_by_count":16,"area":"alignment"},{"id":"2411.00418","title":"Self-Evolved Reward Learning for LLMs","created":"2024-11-01","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":"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":"2407.10944","title":"Naturally Occurring Feedback is Common, Extractable and Useful","created":"2024-07-15","cited_by_count":14,"area":"alignment"},{"id":"2509.07150","title":"PLaID++: A Preference Aligned Language Model for Targeted Inorganic Materials Design","created":"2025-09-08","cited_by_count":14,"area":"alignment"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2505.10527","title":"WorldPM: Scaling Human Preference Modeling","created":"2025-05-15","cited_by_count":13,"area":"alignment"},{"id":"2406.07780","title":"A Critical Look At Tokenwise Reward-Guided Text Generation","created":"2024-06-12","cited_by_count":12,"area":"alignment"},{"id":"2410.03717","title":"Revisiting the Superficial Alignment Hypothesis","created":"2024-09-27","cited_by_count":12,"area":"alignment"},{"id":"2506.04118","title":"Guided Speculative Inference for Efficient Test-Time Alignment of LLMs","created":"2025-06-04","cited_by_count":11,"area":"alignment"},{"id":"2505.12225","title":"Mining Intrinsic Rewards from LLM Hidden States for Efficient Best-of-N Sampling","created":"2025-05-18","cited_by_count":9,"area":"alignment"},{"id":"2406.18777","title":"Aligning Model Properties via Conformal Risk Control","created":"2024-06-26","cited_by_count":7,"area":"alignment"},{"id":"2407.06542","title":"LIONs: An Empirically Optimized Approach to Align Language Models","created":"2024-07-09","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":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2309.02884","title":"Aligning Large Language Models for Clinical Tasks","created":"2023-09-06","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":"2511.02109","title":"Deep Value Benchmark: Measuring Whether Models Generalize Deep Values or Shallow Preferences","created":"2025-11-03","cited_by_count":6,"area":"alignment"},{"id":"2605.02946","title":"RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2502.13177","title":"KL Penalty Control via Perturbation for Direct Preference Optimization","created":"2025-02-18","cited_by_count":5,"area":"alignment"},{"id":"2502.17927","title":"Advantage-Guided Distillation for Preference Alignment in Small Language Models","created":"2025-02-25","cited_by_count":5,"area":"alignment"},{"id":"2506.03968","title":"From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding","created":"2025-06-04","cited_by_count":5,"area":"alignment"},{"id":"2506.04679","title":"Normative Conflicts and Shallow AI Alignment","created":"2025-06-05","cited_by_count":5,"area":"alignment"},{"id":"2406.10307","title":"What is the best model? Application-driven Evaluation for Large Language Models","created":"2024-06-14","cited_by_count":4,"area":"alignment"},{"id":"2412.10689","title":"Learning to Verify Summary Facts with Fine-Grained LLM Feedback","created":"2024-12-14","cited_by_count":4,"area":"alignment"},{"id":"2502.05400","title":"Dynamic Noise Preference Optimization: Self-Improvement of Large Language Models with Self-Synthetic Data","created":"2025-02-08","cited_by_count":4,"area":"alignment"},{"id":"2503.20194","title":"GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization","created":"2025-03-26","cited_by_count":4,"area":"alignment"},{"id":"2505.03059","title":"Improving Model Alignment Through Collective Intelligence of Open-Source LLMS","created":"2025-05-05","cited_by_count":4,"area":"alignment"},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2505.11790","title":"JULI: Jailbreak Large Language Models by Self-Introspection","created":"2025-05-17","cited_by_count":3,"area":"alignment"},{"id":"2509.13869","title":"Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs","created":"2025-09-17","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":"2601.12535","title":"Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning","created":"2026-01-18","cited_by_count":3,"area":"alignment"},{"id":"2602.08829","title":"WildReward: Learning Reward Models from In-the-Wild Human Interactions","created":"2026-02-09","cited_by_count":3,"area":"alignment"},{"id":"2603.06797","title":"Best-of-Tails: Bridging Optimism and Pessimism in Inference-Time Alignment","created":"2026-03-06","cited_by_count":3,"area":"alignment"},{"id":"2406.04583","title":"Extroversion or Introversion? Controlling The Personality of Your Large Language Models","created":"2024-06-07","cited_by_count":2,"area":"alignment"},{"id":"2406.10813","title":"Self-Evolution Fine-Tuning for Policy Optimization","created":"2024-06-16","cited_by_count":2,"area":"alignment"},{"id":"2410.12194","title":"Negative-Prompt-driven Alignment for Generative Language Model","created":"2024-10-16","cited_by_count":2,"area":"alignment"},{"id":"2410.13785","title":"PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment","created":"2024-10-17","cited_by_count":2,"area":"alignment"},{"id":"2509.26074","title":"Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis","created":"2025-09-30","cited_by_count":2,"area":"alignment"},{"id":"2603.03326","title":"Controllable and explainable personality sliders for LLMs at inference time","created":"2026-02-10","cited_by_count":2,"area":"alignment"},{"id":"2603.13506","title":"LibraGen: Playing a Balance Game in Subject-Driven Video Generation","created":"2026-03-13","cited_by_count":2,"area":"alignment"},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2503.07660","title":"Research Superalignment Should Advance Now with Alternating Competence and Conformity Optimization","created":"2025-03-08","cited_by_count":1,"area":"alignment"},{"id":"2505.19700","title":"Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models","created":"2025-05-26","cited_by_count":1,"area":"alignment"},{"id":"2506.03827","title":"Multi-objective Aligned Bidword Generation Model for E-commerce Search Advertising","created":"2025-06-04","cited_by_count":1,"area":"alignment"},{"id":"2508.07638","title":"Data Selection for LLM Alignment Using Fine-Grained Preferences","created":"2025-08-11","cited_by_count":1,"area":"alignment"},{"id":"2512.15765","title":"Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization","created":"2025-12-12","cited_by_count":1,"area":"alignment"},{"id":"2601.03401","title":"Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms","created":"2026-01-06","cited_by_count":1,"area":"alignment"},{"id":"2601.06238","title":"SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers","created":"2026-01-08","cited_by_count":1,"area":"alignment"},{"id":"2601.10986","title":"ZPD Detector: Data Selection via Capability-Difficulty Alignment for Large Language Models","created":"2026-01-16","cited_by_count":1,"area":"alignment"},{"id":"2605.20285","title":"Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2606.00813","title":"Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs","created":"2026-05-30","cited_by_count":1,"area":"alignment"},{"id":"2302.12349","title":"Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws","created":"2023-02-23","cited_by_count":0,"area":"alignment"},{"id":"2409.02118","title":"TSO: Self-Training with Scaled Preference Optimization","created":"2024-08-31","cited_by_count":0,"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":"2505.23788","title":"Nine Ways to Break Copyright Law and Why Our LLM Won't: A Fair Use Aligned Generation Framework","created":"2025-05-25","cited_by_count":0,"area":"alignment"},{"id":"2506.09329","title":"Towards Efficient and Effective Alignment of Large Language Models","created":"2025-06-11","cited_by_count":0,"area":"alignment"},{"id":"2512.02409","title":"Data Curation Through the Lens of Spectral Dynamics: Static Limits, Dynamic Acceleration, and Practical Oracles","created":"2025-12-02","cited_by_count":0,"area":"alignment"},{"id":"2512.07059","title":"Replicating TEMPEST at Scale: Multi-Turn Adversarial Attacks Against Trillion-Parameter Frontier Models","created":"2025-12-08","cited_by_count":0,"area":"alignment"},{"id":"2602.24082","title":"Preference Packing: Efficient Preference Optimization for Large Language Models","created":"2026-02-27","cited_by_count":0,"area":"alignment"},{"id":"2603.17378","title":"Efficient Exploration at Scale","created":"2026-03-18","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}