教大模型在何时该搜索，提升问答准确率。
When Should LLMs Search? Counterfactual Supervision for Search Routing
- 通过对比无搜索与强制搜索结果，构建决策监督信号。
- 模型搜索路由准确率提升，Gemma和Qwen分别达0.8235和0.8365。
- 适合需要优化搜索决策的LLM应用开发者参考。
增强搜索的语言模型可通过外部证据弥补参数化知识的不足，但搜索并非总有益：模型可能对本可回答的问题调用搜索，或在应修正、澄清或放弃时依赖噪声证据。本文将此问题建模为实例级搜索路由任务：判断是否需搜索以提升任务成功率。通过比较同一问题的无搜索与强制搜索结果，基于任务特定成功构建关于‘无搜索’、‘搜索’、‘未解决’的最优策略。以此最优策略作为评估标准与学习信号，采用监督微调与偏好优化训练搜索路由策略，在Gemma E2B和Qwen3.5-4B上，路由宏平均F1分别从0.7082提升至0.8235，从0.7053提升至0.8365。进一步分析显示，学习到的策略有效减少模型特异性路由失败：Gemma主要学会避免无意义搜索，而Qwen进一步减少遗漏搜索；残余未解决案例揭示了涉及模型能力、检索预算、证据利用及策略行为的异质性瓶颈。
原文摘要 · Abstract (English)
Search-augmented language models can use external evidence to compensate for limitations in parametric knowledge, but search is not uniformly beneficial: models may call search for questions they can already answer, or rely on noisy evidence when correction, clarification, or abstention would be more appropriate. We formulate this as an instance-level search-routing problem: deciding whether search is needed to improve task success relative to a no-search execution. To derive supervision, we compare no-search and forced-search outcomes for the same question and construct an oracle over NO SEARCH, SEARCH, and UNSOLVED based on task-specific success. Using this oracle as both an evaluation criterion and a learning signal, we train search-routing policies with supervised fine-tuning and preference optimization, improving routing macro-F1 on oracle-eligible examples from 0.7082 to 0.8235 for Gemma E2B and from 0.7053 to 0.8365 for Qwen3.5-4B. Further analysis shows that the learned policies reduce model-specific routing failures: Gemma primarily learns no-search restraint, while Qwen further reduces missed search; residual UNSOLVED cases reveal heterogeneous bottlenecks involving model capacity, retrieval budget, evidence use, and policy behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。