QuIM-RAG retrieves chunks by matching a user question to LLM-generated questions from each chunk in a quantized embedding space, reporting higher QA scores than a traditional RAG baseline on an NDSU website corpus.
QUADRo: Dataset and Models for QUestion-Answer Database Retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
An effective paradigm for building Automated Question Answering systems is the re-use of previously answered questions, e.g., for FAQs or forum applications. Given a database (DB) of question/answer (q/a) pairs, it is possible to answer a target question by scanning the DB for similar questions. In this paper, we scale this approach to open domain, making it competitive with other standard methods, e.g., unstructured document or graph based. For this purpose, we (i) build a large scale DB of 6.3M q/a pairs, using public questions, (ii) design a new system based on neural IR and a q/a pair reranker, and (iii) construct training and test data to perform comparative experiments with our models. We demonstrate that Transformer-based models using (q,a) pairs outperform models only based on question representation, for both neural search and reranking. Additionally, we show that our DB-based approach is competitive with Web-based methods, i.e., a QA system built on top the BING search engine, demonstrating the challenge of finding relevant information. Finally, we make our data and models available for future research.
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance
QuIM-RAG retrieves chunks by matching a user question to LLM-generated questions from each chunk in a quantized embedding space, reporting higher QA scores than a traditional RAG baseline on an NDSU website corpus.