Question-Based Retrieval using Atomic Units for Enterprise RAG

Vatsal Raina, Mark Gales


Abstract
Enterprise retrieval augmented generation (RAG) offers a highly flexible framework for combining powerful large language models (LLMs) with internal, possibly temporally changing, documents. In RAG, documents are first chunked. Relevant chunks are then retrieved for a user query, which are passed as context to a synthesizer LLM to generate the query response. However, the retrieval step can limit performance, as incorrect chunks can lead the synthesizer LLM to generate a false response. This work applies a zero-shot adaptation of standard dense retrieval steps for more accurate chunk recall. Specifically, a chunk is first decomposed into atomic statements. A set of synthetic questions are then generated on these atoms (with the chunk as the context). Dense retrieval involves finding the closest set of synthetic questions, and associated chunks, to the user query. It is found that retrieval with the atoms leads to higher recall than retrieval with chunks. Further performance gain is observed with retrieval using the synthetic questions generated over the atoms. Higher recall at the retrieval step enables higher performance of the enterprise LLM using the RAG pipeline.
Anthology ID:
2024.fever-1.25
Volume:
Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER)
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Michael Schlichtkrull, Yulong Chen, Chenxi Whitehouse, Zhenyun Deng, Mubashara Akhtar, Rami Aly, Zhijiang Guo, Christos Christodoulopoulos, Oana Cocarascu, Arpit Mittal, James Thorne, Andreas Vlachos
Venue:
FEVER
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
219–233
Language:
URL:
https://aclanthology.org/2024.fever-1.25
DOI:
Bibkey:
Cite (ACL):
Vatsal Raina and Mark Gales. 2024. Question-Based Retrieval using Atomic Units for Enterprise RAG. In Proceedings of the Seventh Fact Extraction and VERification Workshop (FEVER), pages 219–233, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Question-Based Retrieval using Atomic Units for Enterprise RAG (Raina & Gales, FEVER 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.fever-1.25.pdf