DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911218427494400 |
|---|---|
| author | Wang, Changhao Liu, Yanfang Fan, Xinxin Zhou, Anzhi Tian, Lao Lu, Yunfeng |
| author_facet | Wang, Changhao Liu, Yanfang Fan, Xinxin Zhou, Anzhi Tian, Lao Lu, Yunfeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16302 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA Wang, Changhao Liu, Yanfang Fan, Xinxin Zhou, Anzhi Tian, Lao Lu, Yunfeng Artificial Intelligence Information Retrieval 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. |
| title | DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA |
| topic | Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2510.16302 |