Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

2020/09/27 by Xiong, Wenhan, Li, Xiang Lorraine, Iyer, Srini +8 · 12 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2009.12756

Abstract

We propose a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on two multi-hop datasets, HotpotQA and multi-evidence FEVER. Contrary to previous work, our method does not require access to any corpus-specific information, such as inter-document hyperlinks or human-annotated entity markers, and can be applied to any unstructured text corpus. Our system also yields a much better efficiency-accuracy trade-off, matching the best published accuracy on HotpotQA while being 10 times faster at inference time.

Cited by

• KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems
• HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering
• Modeling Contextual Passage Utility for Multihop Question Answering
• E-CARE: An Efficient LLM-based Commonsense-Augmented Framework for E-Commerce
• PROPEX-RAG: Enhanced GraphRAG using Prompt-Driven Prompt Execution
• RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability
• PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering
• Taming a Retrieval Framework to Read Images in Humanlike Manner for Augmenting Generation of MLLMs
• Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning
• Enhancing Factual Accuracy and Citation Generation in LLMs via Multi-Stage Self-Verification
• SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval
• AgriGPT: a Large Language Model Ecosystem for Agriculture

Related

• Combining Lexical and Dense Retrieval for Computationally Efficient Multi-hop Question Answering
• Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
• HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions
• Answering Complex Open-domain Questions Through Iterative Query Generation
• Multi-step Entity-centric Information Retrieval for Multi-Hop Question\n Answering