A document hypercube with LLM-extracted labels and hybrid sparse/dense matching improves retrieval and QA accuracy over RAG baselines on three datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hypercube-Based Retrieval-Augmented Generation for Scientific Question-Answering
A document hypercube with LLM-extracted labels and hybrid sparse/dense matching improves retrieval and QA accuracy over RAG baselines on three datasets.