DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
Authors:
- Changhao WangCWChanghao Wang
- Yanfang LiuYLYanfang Liu
- Xinxin FanXFXinxin Fan
- Anzhi ZhouAZAnzhi Zhou
- Lao TianLTLao Tian
- Yunfeng LuYLYunfeng Lu
Preprint
Abstract
Multi-hop reasoning for question answering (QA) plays a critical role in retrieval-augmented generation (RAG) for modern large language models (LLMs). The accurate answer can be obtained through retrieving relational structure of entities from knowledge graph (KG). Regarding the inherent relation-dependency and reasoning pattern, multi-hop reasoning can be in general classified into two categories: i) parallel fact-verification multi-hop reasoning question, i.e., requiring simultaneous verifications of multiple independent sub-questions; and ii) chained multi-hop reasoning questions, i.e., demanding sequential multi-step inference with intermediate conclusions serving as essential premises for subsequent reasoning. Currently, the multi-hop reasoning approaches singly employ one of two techniques: LLM response-based fact verification and KG path-based chain construction. Nevertheless, the former excels at parallel fact-verification but underperforms on chained reasoning tasks, while the latter demonstrates proficiency in chained multi-hop reasoning but suffers from redundant path retrieval when handling parallel fact-verification reasoning. These limitations deteriorate the efficiency and accuracy for multi-hop QA tasks. To address this challenge, we propose a novel dual-track KG verification and reasoning framework DTKG, which is inspired by the Dual Process Theory in cognitive science. Specifically, DTKG comprises two main stages: the Classification Stage and the Branch Processing Stage.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Noisy Pair Corrector for Dense Retrieval2023
- ♫ MuSiQue: Multihop Questions via Single-hop Question CompositionTransactions of the Association for Computational Linguistics, 2022
- Retrieval Augmentation for Commonsense Reasoning: A Unified Approach2022
- Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity2022
- PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text2019
- ERNIE: Enhanced Language Representation with Informative Entities2019
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering2018
- Urbanity2017
- Dual-Processing Accounts of Reasoning, Judgment, and Social CognitionAnnual Review of Psychology, 2008
- In two minds: dual-process accounts of reasoningTrends in Cognitive Sciences, 2003