cs.CLOct 30, 2026

DecisionRank: On-Policy Distillation for Decision-Model Rerankers

Authors: Yanran Wu, Dian Yu, Chongyang Bai, Jieyi Zhang, Rui Liu, Tianyi Chen, Shike Mei, Hang Cui, 

Organizations: Meta · Purdue University

Abstract

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 sequences, while the student determines the ranking using scores from the first-token position. To bridge this gap, we introduce DecisionRank, a decision model trained through item-space on-policy distillation (OPD). Item-space OPD constructs the student's rollout by sorting its document scores into a ranked sequence. A generative teacher takes the resulting ranking list as inputs and provides conditional feedback to directly supervise those scores. Combined with offline ranking supervision, DecisionRank achieves state-of-the-art performance on both general and reasoning-intensive retrieval benchmarks such as TREC DL, BEIR, and BRIGHT. Across four benchmarks, item-space OPD consistently outperforms alternative training objectives. Even at 1.7B parameters, DecisionRank surpasses its 27B generative teacher on TREC DL19--23. At 8B, it outperforms its generative listwise counterpart while running 24.5×24.5\times faster on TREC DL and 16.7×16.7\times faster on BRIGHT.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Can System-1-Style Decision Models Replace Dedicated Rerankers in RAG? A Systems Evaluation

    Oct 26, 2026Qiaomu Li, Ying XieLLM RerankingRAG Evaluation

  2. Retriever-Free Retrieval: Navigating Documents with Decision Models

    Oct 26, 2026Chao Wan, Paul Jünger, Beixi Du +3Knowledge Retrieval in Language ModelsInformation Retrieval

  3. SPD: Single Pass Decoding for Generative Reranking

    Sep 1, 2026Emil Laftchiev, Prachi Agrawal, Moe Kayali +7Language Model DecodingLLM Reranking