{"total":11,"rows":[{"id":"2507.06187","title":"The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains","created":"2025-07-08","cited_by_count":28,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2508.06482","title":"Post-training for Efficient Communication via Convention Formation","created":"2025-08-08","cited_by_count":7,"area":null},{"id":"2502.10505","title":"Preference learning made easy: Everything should be understood through win rate","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2605.08666","title":"The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2606.06667","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2506.08616","title":"Generalizing while preserving monotonicity in comparison-based preference learning models","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2505.23933","title":"BIRD: Behavior Induction via Representation-structure Distillation","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2609.40165","title":"PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}