Papers by Jeongsoo Lee

1 papers
GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation (2025.findings-emnlp)

Copied to clipboard

Challenge: Current evaluations of RAG systems overlook structural complexity and multi-step reasoning . GRADE model enables fine-grained analysis of Ragging performance .
Approach: They propose a framework that models retrieval difficulty along two orthogonal dimensions . they extract knowledge graphs and augment them through semantic clustering to recover missing links .
Outcome: The proposed framework models retrieval difficulty along two orthogonal dimensions . error rates correlate with the framework, and it validates its diagnostic utility.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations