Large Language Models ↔ multi-hop knowledge base question answering

Relations (1)

related 0.70 — strongly supporting 7 facts

Large Language Models are utilized as the core reasoning engines in frameworks like HOLMES, GMeLLo, and SG-RAG to perform multi-hop knowledge base question answering by integrating external knowledge graphs [1], [2], [3]. These hybrid approaches leverage the linguistic capabilities of LLMs to facilitate complex reasoning tasks such as question decomposition and iterative multi-hop retrieval [4], [5], [6].

Facts (7)

Sources

Large Language Models Meet Knowledge Graphs for Question ... arxiv.org arXiv 7 facts

referencePanda et al. (2024) published 'HOLMES: Hyper-relational knowledge graphs for multi-hop question answering using LLMs' in ACL, pages 13263–13282, which introduces the HOLMES framework for multi-hop question answering using hyper-relational knowledge graphs.

referenceQiao et al. (2024) published 'GraphLLM: A general framework for multi-hop question answering over knowledge graphs using large language models' in NLPCC, pages 136–148, detailing a framework for multi-hop reasoning.

referenceSaleh et al. (2024) published 'SG-RAG: Multi-hop question answering with large language models through knowledge graphs' in ICNLSP, pages 439–448, presenting a method for multi-hop QA using knowledge graphs.

referenceHOLME utilizes a context-aware retrieved and pruned hyper-relational knowledge graph, constructed based on an entity-document graph, to enhance large language models for generating answers in multi-hop question-answering.

claimHybrid methods for synthesizing LLMs and KGs support multi-doc, multi-modal, multi-hop, conversational, XQA, and temporal QA tasks.

claimFusing knowledge from LLMs and Knowledge Graphs augments question decomposition in multi-hop Question Answering, facilitating iterative reasoning to generate accurate final answers.

referenceGMeLLo integrates explicit knowledge from knowledge graphs with linguistic knowledge from large language models for multi-hop question-answering by introducing fact triple extraction, relation chain extraction, and query and answer generation.