{"total":39,"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":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185,"area":"alignment"},{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2402.09267","title":"Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation","created":"2024-02-14","cited_by_count":80,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"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":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2602.19313","title":"TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics","created":"2026-02-22","cited_by_count":33,"area":"alignment"},{"id":"2409.05283","title":"On the Relationship between Truth and Political Bias in Language Models","created":"2024-09-09","cited_by_count":31,"area":"alignment"},{"id":"2409.18786","title":"A Survey on the Honesty of Large Language Models","created":"2024-09-27","cited_by_count":23,"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":"2507.11316","title":"Internal Value Alignment in Large Language Models through Controlled Value Vector Activation","created":"2025-07-15","cited_by_count":16,"area":"alignment"},{"id":"2503.01048","title":"Personalize Your LLM: Fake it then Align it","created":"2025-03-02","cited_by_count":15,"area":"alignment"},{"id":"2603.04069","title":"Monitoring Emergent Reward Hacking During Generation via Internal Activations","created":"2026-03-04","cited_by_count":14,"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":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"id":"2311.07723","title":"Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains","created":"2023-11-13","cited_by_count":8,"area":"alignment"},{"id":"2403.06326","title":"From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification","created":"2024-03-10","cited_by_count":8,"area":"alignment"},{"id":"2405.18718","title":"Efficient Model-agnostic Alignment via Bayesian Persuasion","created":"2024-05-29","cited_by_count":8,"area":"alignment"},{"id":"2501.10639","title":"Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks","created":"2025-01-18","cited_by_count":7,"area":"alignment"},{"id":"2604.01476","title":"From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering","created":"2026-04-01","cited_by_count":7,"area":"alignment"},{"id":"2310.19347","title":"Improving Factual Consistency of News Summarization by Contrastive Preference Optimization","created":"2023-10-30","cited_by_count":6,"area":"alignment"},{"id":"2406.08124","title":"Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2602.00986","title":"Sparse Reward Subsystem in Large Language Models","created":"2026-02-01","cited_by_count":4,"area":"alignment"},{"id":"2606.32032","title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","created":"2026-06-30","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":"2509.23982","title":"Toward Preference-aligned Large Language Models via Residual-based Model Steering","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2508.14853","title":"Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent","created":"2025-08-20","cited_by_count":2,"area":"alignment"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2511.21737","title":"Polarity-Aware Probing for Quantifying Latent Alignment in Language Models","created":"2025-11-21","cited_by_count":1,"area":"alignment"},{"id":"2602.23391","title":"Detoxifying LLMs via Representation Erasure-Based Preference Optimization","created":"2026-02-24","cited_by_count":1,"area":"alignment"},{"id":"2604.27401","title":"Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs","created":"2026-04-30","cited_by_count":1,"area":"alignment"},{"id":"2609.22219","title":"Knowing, and Saying It Only When Asked: LLM Endognostics and the Schizognosis of Minerva-7B","created":"2026-09-02","cited_by_count":1,"area":"alignment"},{"id":"2608.03892","title":"Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition","created":"2026-08-04","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":"2610.12707","title":"Unsupervised Multimodal Reward Modeling","created":"2026-10-08","cited_by_count":0,"area":"alignment"},{"id":"2610.19365","title":"DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment","created":"2026-10-14","cited_by_count":0,"area":"alignment"}],"next_cursor":null}