--- format: "aidr-story-markdown/v1" id: "f11f5caf5b4a9453c61b7e316a5023a68d067863906e9ebc6c3b18464f1565b8" canonical_url: "https://aidr.today/f11f5caf?lang=en" title: "DecisionRank: On-Policy Distillation for Decision-Model Rerankers" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-11-03T00:00:00.000Z" category: "Research" topics: ["llm"] source_urls: ["https://huggingface.co/papers/2610.42128"] summary: "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." --- # DecisionRank: On\-Policy Distillation for Decision\-Model Rerankers > [Open the canonical story]() **Published:** 2026-11-03T00:00:00.000Z **Category:** Research **Topics:** llm ## Summary 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\. ## Sources - [Story source]()