跳到正文
arXiv cs.AI· Seiya Kawano, Koji Marusaki, Hirofumi Nonaka, Koichiro Yoshino·· 4 小时前AI 评分26

从搜索反馈中教语言模型收窄布尔专利检索

Teaching Language Models to Narrow Boolean Patent Searches from Search Feedback

AI 导读

研究将 38,397 份日本专利局检索报告蒸馏为可执行的专家策略,并据此训练生成器收窄布尔检索式。行级“保留引用的收窄信用”在筛选指标上优于策略级评分,迭代后把含引用的中位结果集从 768 篇压到 50 篇以内,使更多引用落入 100 篇以下的集合,但召回率低于专家;策略级偏好学习则接近完整召回,两种方式互补。

正文 · 原文

View PDF HTML (experimental)

Abstract:Patent prior-art searchers issue Boolean queries line by line, broadening to find relevant documents and narrowing until candidates can be screened. We distill 38,397 Japan Patent Office search reports into executable expert strategies, re-execute them, and evaluate generated strategies by citation recall and the smallest set containing each citation. Prompted models write valid, high-recall strategies but leave citations in sets too large to screen. We adapt a generator offline from scored rollouts in two forms: strategy-level learning from a screening-aware strategy score, and line-level learning from citation-preserving narrowing credit, which upweights the query lines keeping a found citation in a smaller set. On shared rollouts, line-level credit outperforms strategy-level scores on screening measures; iterated, it cuts the median citation-containing set from 768 to under 50 and places more citations in sets under 100 documents than experts, at lower recall. Strategy-level preference learning reaches near-complete recall; the two forms are complementary.
Comments: 13 pages, 3 figures, 3 tables. Accepted at NLPIR 2026
Subjects: Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2611.22270 [cs.IR]
  (or arXiv:2611.22270v1 [cs.IR] for this version)
  https://doi.org/10.48550/arXiv.2611.22270

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Seiya Kawano [view email]
[v1] Tue, 17 Nov 2026 06:17:43 UTC (91 KB)

来源:arXiv cs.AI · arxiv.org