{"total":18,"rows":[{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96,"area":"alignment"},{"id":"2312.07000","title":"Alignment for Honesty","created":"2023-12-12","cited_by_count":74,"area":"alignment"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2412.00967","title":"Linear Probe Penalties Reduce LLM Sycophancy","created":"2024-12-01","cited_by_count":28,"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":"2602.01002","title":"How RLHF Amplifies Sycophancy","created":"2026-02-01","cited_by_count":23,"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":"2510.26707","title":"Value Drifts: Tracing Value Alignment During LLM Post-Training","created":"2025-10-30","cited_by_count":10,"area":"alignment"},{"id":"2411.10156","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","created":"2024-11-15","cited_by_count":5,"area":"alignment"},{"id":"2604.05279","title":"Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition","created":"2026-04-07","cited_by_count":4,"area":"alignment"},{"id":"2311.07587","title":"Frontier Language Models are not Robust to Adversarial Arithmetic, or \"What do I need to say so you agree 2+2=5?","created":"2023-11-08","cited_by_count":3,"area":"alignment"},{"id":"2604.10585","title":"Calibration Collapse Under Sycophancy Fine-Tuning: How Reward Hacking Breaks Uncertainty Quantification in LLMs","created":"2026-04-12","cited_by_count":3,"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":"2604.26511","title":"Tatemae: Detecting Alignment Faking via Tool Selection in LLMs","created":"2026-04-29","cited_by_count":1,"area":"alignment"},{"id":"2605.27382","title":"The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs","created":"2026-04-10","cited_by_count":1,"area":"alignment"},{"id":"2603.16417","title":"Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences","created":"2026-03-17","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":"2610.02568","title":"Mitigating Social Sycophancy via Pluralistic Preference Optimization","created":"2026-10-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}