Improving Information Extraction with Learned Queries
When information extraction fails, a natural instinct is to improve the model doing it: for example, by scaling it up or refining its reasoning. In this paper, we show that another part of the pipeline matters at least as much: the queries used to elicit this information. Across four clinical benchmarks and five LLMs, improving the question design alone raises performance by 18.6 F1-score points, i.e. more than using larger extraction models. To make such question design learnable, we introduce List of Questions (LoQ), which generates document-specific question sets, and FeedQ, a feedback-driv
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%RAGless: Q-Q retrieval with score aggregation for closed-domain FAQ [P] →
- PossiblePossibly related (embedding) · 47%Open-weight 4B models approach o3-level medical question answering in Swedish [P] →
- LinkedLinked via arxiv author · 85%Omar Sharif →
“Improving Information Extraction with Learned Queries”
- LinkedLinked via arxiv author · 85%Soroush Vosoughi →
“Improving Information Extraction with Learned Queries”
- LinkedLinked via arxiv author · 85%Nikhil Singh →
“Improving Information Extraction with Learned Queries”
- PossiblePossibly related (embedding) · 47%Outcome reward models improve LLM-based Text-to-SQL generation with GradeSQL - Bioengineer.org →