DecisionRank：用在线策略蒸馏训练决策模型重排器

Authors:Yanran Wu, Dian Yu, Chongyang Bai, Jieyi Zhang, Rui Liu, Tianyi Chen, Shike Mei, Hang Cui, Frank Shyu, Sandeep Pandey, Luke Simon, Chunwei Liu, Xi Liu

View PDF HTML (experimental)

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 $24.5\times$ faster on TREC DL and $16.7\times$ faster on BRIGHT.

Submission history

From: Yanran Wu [view email]
[v1] Fri, 30 Oct 2026 17:56:58 UTC (686 KB)