# DecisionRank: On-Policy Distillation for Decision-Model Rerankers

> Source: <https://aiflash.com/news/144507/>
> Published: 2026-11-03 03:00:31+00:00

Decision models target structured tasks by directly predicting choices or scores, avoiding autoregressive decoding latency. However, transferring a generative LLM's ranking knowledge to a decision model remains challenging: the teacher expresses preferences through a ranked list of document ID seque