{"ID":2853305,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.16302","arxiv_id":"2510.16302","title":"DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA","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.","short_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 reasoni...","url_abs":"https://arxiv.org/abs/2510.16302","url_pdf":"https://arxiv.org/pdf/2510.16302v1","authors":"[\"Changhao Wang\",\"Yanfang Liu\",\"Xinxin Fan\",\"Anzhi Zhou\",\"Lao Tian\",\"Yunfeng Lu\"]","published":"2025-10-18T02:19:11Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.IR\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}