AI & ML
Teaching Language Models to Narrow Boolean Patent Searches from Search Feedback
arXiv cs.IR0 views
arXiv:2611.22270v1 Announce Type: new 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.
Source:https://arxiv.org/abs/2611.22270PreviousCluster-Guided Decoding with Trust-Region Constraints for Personalized RecommendationNextNONSENSE: Non-Semantic Strings Expose Semanticity Gaps in Dense Retrieval
Related posts

The UK and some other countries don’t get more Siri AI usage with iCloud+
09to5Mac

MacPaw’s Moonlock comes to iPhone, helping users detect potential scams
09to5Mac

Six new Aqara smart lights with Apple Home support and ‘spatial intelligence’
09to5Mac

Leaker claims Apple developing four models of 20th anniversary iPhone
09to5Mac

The Download: AI learns to smell and hydropower struggles
0MIT Technology Review

Nvidia isn’t selling any more AI chips to China
0The Verge