Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering

arXiv:2403.05217v1 Announce Type: new
Abstract: Open-domain question answering (ODQA) has emerged as a pivotal research spotlight in information systems. Existing methods follow two main paradigms to collect evidence: (1) The \textit{retrieve-then-read} paradigm retrieves pertinent documents from an external corpus; and (2) the \textit{generate-then-read} paradigm employs large language models (LLMs) to generate relevant documents. However, neither can fully address multifaceted requirements for evidence. To this end, we propose LLMQA, a generalized framework that formulates the ODQA process into three basic steps: …

abstract arxiv capabilities cs.ai cs.cl cs.ir documents domain evidence generate information language language models large language large language models llms paradigm pivotal question question answering research role spotlight systems type