RAG-based Question Answering over Heterogeneous Data and Text

Autor:	Christmann, Philipp, Weikum, Gerhard
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Information Retrieval
Druh dokumentu:	Working Paper
Popis:	This article presents the QUASAR system for question answering over unstructured text, structured tables, and knowledge graphs, with unified treatment of all sources. The system adopts a RAG-based architecture, with a pipeline of evidence retrieval followed by answer generation, with the latter powered by a moderate-sized language model. Additionally and uniquely, QUASAR has components for question understanding, to derive crisper input for evidence retrieval, and for re-ranking and filtering the retrieved evidence before feeding the most informative pieces into the answer generation. Experiments with three different benchmarks demonstrate the high answering quality of our approach, being on par with or better than large GPT models, while keeping the computational cost and energy consumption orders of magnitude lower. Comment: IEEE Data Engineering Bulletin -- December 2024 Edition on RAG
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.07420 Zobrazit plný text záznamu View this record from Arxiv