RAG-based Question Answering over Heterogeneous Data and Text
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Answer GenerationKnowledge GraphsLanguage ModelingLanguage ModellingQuestion AnsweringRAGRe-RankingRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data
Existing question answering datasets focus on dealing with homogeneous information, based either only on text or KB/Table information alone. However, as human knowledge is distributed over heterogeneous forms, using homo…
Multi-hop Question AnsweringQuestion AnsweringHybrid-SQuAD: Hybrid Scholarly Question Answering Dataset
Existing Scholarly Question Answering (QA) methods typically target homogeneous data sources, relying solely on either text or Knowledge Graphs (KGs). However, scholarly information often spans heterogeneous sources, nec…
Knowledge GraphsLanguage ModelingLanguage ModellingLarge Language Model+2Reasoning over Hybrid Chain for Table-and-Text Open Domain Question Answering
Tabular and textual question answering requires systems to perform reasoning over heterogeneous information, considering table structure, and the connections among table and text. In this paper, we propose a ChAin-centri…
Open-Domain Question AnsweringQuestion AnsweringFaithful Temporal Question Answering over Heterogeneous Sources
Temporal question answering (QA) involves time constraints, with phrases such as "... in 2019" or "... before COVID". In the former, time is an explicit condition, in the latter it is implicit. State-of-the-art methods h…
Question AnsweringConversational Question Answering on Heterogeneous Sources
Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a kn…
Conversational Question AnsweringDecoderQuestion Answering