arXiv:2510.18913v5 Announce Type: replace-cross
Abstract: Direct Preference Optimization (DPO) is effective but brittle under annotator noise and distribution shift because it operates on hard, pairwise labels and only regularizes log-probability differences. We introduce Anchored Direct Preference Optimization (ADPO), a framework that extends preference learning to soft listwise supervision via reference anchoring. ADPO minimizes KL(q || softmax((s – s_ref) / tau_anc)), which (i) recovers supervised fine-tuning, knowledge distillation, maximum-entropy reinforcement learning, and DPO as special cases through suitable choices of target q, anchor policy, and temperature; (ii) induces an implicit trust region governed by the softmax Fisher metric, independent of the anchor; and (iii) supports stable dynamic-anchor updates. Empirically, we observe a task-dependent tradeoff: dynamic anchors improve online exploration under noise, while fixed anchors excel at offline distillation, achieving up to 170 to 5000 times reduction in student-teacher KL on our benchmarks.
OptoLoop: An optogenetic tool to probe the functional role of genome organization
The genome folds inside the cell nucleus into hierarchical architectural features, such as chromatin loops and domains. If and how this genome organization influences the