{"total":47,"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":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315,"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":"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":"2307.16039","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","created":"2023-07-29","cited_by_count":190,"area":"alignment"},{"id":"2405.08448","title":"Understanding the performance gap between online and offline alignment algorithms","created":"2024-05-14","cited_by_count":110,"area":"alignment"},{"id":"2402.01694","title":"ARGS: Alignment as Reward-Guided Search","created":"2024-01-23","cited_by_count":103,"area":"alignment"},{"id":"2402.02416","title":"Aligner: Efficient Alignment by Learning to Correct","created":"2024-02-04","cited_by_count":98,"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":"2310.19677","title":"MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks","created":"2023-10-30","cited_by_count":44,"area":"alignment"},{"id":"2309.03126","title":"Everyone Deserves A Reward: Learning Customized Human Preferences","created":"2023-09-06","cited_by_count":43,"area":"alignment"},{"id":"2309.00754","title":"Efficient RLHF: Reducing the Memory Usage of PPO","created":"2023-09-01","cited_by_count":40,"area":"alignment"},{"id":"2406.16306","title":"Cascade Reward Sampling for Efficient Decoding-Time Alignment","created":"2024-06-24","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":"2403.05171","title":"Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation","created":"2024-03-08","cited_by_count":33,"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":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":"alignment"},{"id":"2403.18742","title":"Understanding the Learning Dynamics of Alignment with Human Feedback","created":"2024-03-27","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":"2310.19080","title":"Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery","created":"2023-10-29","cited_by_count":14,"area":"alignment"},{"id":"2406.01013","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","created":"2024-06-03","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":"2601.22664","title":"Real-Time Aligned Reward Model beyond Semantics","created":"2026-01-30","cited_by_count":13,"area":"alignment"},{"id":"2305.17760","title":"Language Models are Bounded Pragmatic Speakers: Understanding RLHF from a Bayesian Cognitive Modeling Perspective","created":"2023-05-28","cited_by_count":10,"area":"alignment"},{"id":"2407.03856","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","created":"2024-07-04","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":"2410.12491","title":"Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning","created":"2024-10-16","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":"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":"2402.01706","title":"MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds","created":"2024-01-25","cited_by_count":4,"area":"alignment"},{"id":"2311.08487","title":"Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective","created":"2023-11-14","cited_by_count":3,"area":"alignment"},{"id":"2403.16649","title":"CLHA: A Simple yet Effective Contrastive Learning Framework for Human Alignment","created":"2024-03-25","cited_by_count":3,"area":"alignment"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"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":"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":"2607.04640","title":"Wrong Before Right: Late Rescue and Interface Failure in Aligned Language Models","created":"2026-07-06","cited_by_count":1,"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":"2509.12179","title":"Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation","created":"2025-09-15","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":"2601.17260","title":"The Viscosity of Logic: Phase Transitions and Hysteresis in DPO Alignment","created":"2026-01-24","cited_by_count":0,"area":"alignment"},{"id":"2602.02304","title":"Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Explain Behavioral Shifts in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2605.30323","title":"In-Context Reward Adaptation for Robust Preference Modeling","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2609.06934","title":"The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persists","created":"2026-09-07","cited_by_count":0,"area":"alignment"},{"id":"2610.00568","title":"Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.02844","title":"DNAlign: Dynamic Null-Space Safe Alignment for LLMs","created":"2026-10-02","cited_by_count":0,"area":"alignment"}],"next_cursor":null}