EMNLP Findings2025
DCMKC: A Dual Consistency Matching Approach for Multi-hop Question Answering in LLMs
Xinyi Wang, Yiping Song, Chang Liu, Tingjin Luo, Bo Liu, Zheng Xie, Minlie Huang
Abstract
Reasoning based on chains of thought (CoTs) enables large language models (LLMs) to solve problems by thinking step by step and becomes the mainstream solution for Question-Answering (QA) tasks. Knowledge graph (KG)-enhanced CoT technology helps correct factual errors or predict reasoning direction. Existing KG-enhanced methods find relevant information in KGs "within" each reasoning step of CoTs. However, in some cases, logical connections "between" reasoning steps may be missing or wrong, leading to broken reasoning chains and wrong reasoning direction. To solve the above problem, we argue that the errors between reasoning steps require collaborative verification and mining of multiple triplets and multiple paths in KG. So we propose the DCMKC (Dual Consistency Matching for KG and CoT) method, aiming to maintain semantic and structural consistency between KG and CoT. The main idea is to convert CoTs and KGs into two granularity-aligned graphs, transforming multi-hop reasoning and KG matching into iterative matching and modification of two graphs. In each iteration, DCMKC matches the KG reasoning chains with CoTs based on semantic similarity and judges the structural consistency between them. Then it modifies CoTs using the matched chains. After iterations, the CoTs and KG reasoning chains reach high semantic and structural consistency, which is theoretically and experimentally demonstrated by kernel and spectral methods. The two kinds of chains are then used to generate the final answers. Experimental results show that our method outperforms baselines on multiple datasets, especially on multianswer questions, with up to 5.1% improvement over the baseline. Our code is available at https://github.com/suyun417/DCMKC.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph cites Large Language Models are Zero-Shot Reasoners
- DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering cites G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering cites Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering cites Large Language Models are Zero-Shot Reasoners
- Active Retrieval Augmented Generation cites Precise Zero-Shot Dense Retrieval without Relevance Labels
Cited by top-tier papers1
Builds on10
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question AnsweringXiaoxin He, Yijun Tian, Yifei Sun, Nitesh V. Chawla et al.NeurIPS 2024 · 384 citations
- Active Retrieval Augmented GenerationZhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun et al.EMNLP 2023 · 315 citations
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge GraphJiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang et al.ICLR 2024 · 247 citations
- Precise Zero-Shot Dense Retrieval without Relevance LabelsLuyu Gao, Xueguang Ma, Jimmy Lin, Jamie CallanACL 2023 · 211 citations
Related papers
- ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge GraphsMinbae Park, Hyemin Yang, Jeonghyun Kim, Kunsoo Park et al.AAAI 2026
- KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts ReasoningDebjyoti Mondal, Suraj Modi, Subhadarshi Panda, Rituraj Singh et al.AAAI 2024 · 96 citations
- Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge GraphsThi Nguyen, Linhao Luo, Fatemeh Shiri, Dinh Phung et al.ACL Findings 2024 · 17 citations
- Clustering as Reasoning: A -Means Interpretation of Chain-of-Thought Graph LearningXuanting Xie, Zhaochen Guo, Bingheng Li, Xingtong Yu et al.ICML 2026
- Answering Questions by Meta-Reasoning over Multiple Chains of ThoughtOri Yoran, Tomer Wolfson, Ben Bogin, Uri Katz et al.EMNLP 2023 · 30 citations
