• Home
  • Search
  • TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation
  • Open Access IconOpen Access
  • Cite Icon14
  • https://doi.org/10.18653/v1/2024.findings-emnlp.496Copy DOI Icon

TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation

  • Jan 1, 2024
  • Jinyuan Fang +2 more
Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could introduce noise and degrade the performance, especially when handling multi-hop questions that require multiple steps of reasoning. To enhance the multi-hop reasoning ability of RAG models, we propose TRACE1. TRACE constructs knowledge-grounded reasoning chains, which are a series of logically connected knowledge triples, to identify and integrate supporting evidence from the retrieved documents for answering questions. Specifically, TRACE employs a KG Generator to create a knowledge graph (KG) from the retrieved documents, and then uses a novel Autoregressive Reasoning Chain Constructor to build reasoning chains. Experimental results on three multi-hop QA datasets show that TRACE achieves an average performance improvement of up to 14.03% compared to using all the retrieved documents. Moreover, the results indicate that using reasoning chains as context, rather than the entire documents, is often sufficient to correctly answer questions.

Similar Papers
  • Book Chapter
  • Citations7

UNCC Biomedical Semantic Question Answering Systems. BioASQ: Task-7B, Phase-B

  • Jan 01, 2020
  • Sai Krishna Telukuntla +2
  • Research Article
  • Citations177

Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph

  • Apr 25, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Amrita Saha +4
  • Conference Article
  • Citations1

Improving temporal question answering using temporal knowledge graph embedding

  • Apr 07, 2023
  • Jiabao Chen +1
  • Research Article
  • Citations34

No one is perfect: Analysing the performance of question answering components over the DBpedia knowledge graph

  • Aug 05, 2020
  • Journal of Web Semantics
  • Kuldeep Singh +5
  • Research Article

MQPF: A MULTI-DIMENSIONAL QUALITY-AWARE PATH FUSION FRAMEWORK FOR QUESTION ANSWERING

  • Sep 16, 2025
  • Journal of Computer Science and Electrical Engineering
  • Xinyi Wang +1
  • Conference Article

Quantifying Informativeness in Knowledge Graph-Augmented In-Context Learning for Multiple Choice Query Answering

  • Nov 13, 2025
  • Maryam Ghanbari +1
  • Conference Article

International Workshop on Learning with Knowledge Graphs: Construction, Embedding, and Reasoning

  • Feb 27, 2023
  • Qing Li +4
  • Supplementary Content

Towards Complex Question Answering over Knowledge Graphs

  • Dec 14, 2022
  • Fraunhofer-Publica (Fraunhofer-Gesellschaft)
  • Mohnish Dubey
  • Research Article
  • Citations10

Learning structured embeddings of knowledge graphs with generative adversarial framework

  • May 10, 2022
  • Expert Systems with Applications
  • Lu Liu +2
  • Conference Article
  • Citations6

HQADeepHelper: A Deep Learning System for Healthcare Question Answering

  • Apr 20, 2020
  • Feng Luo +5
  • Video Transcripts

Sequence-to-Sequence Knowledge Graph Completion and Question Answering

  • May 07, 2022
  • Underline Science Inc.
  • Rainer Gemulla +2
  • Research Article
  • Citations22

Document GraphRAG: Knowledge Graph Enhanced Retrieval Augmented Generation for Document Question Answering Within the Manufacturing Domain

  • May 22, 2025
  • Electronics
  • Simon Knollmeyer +2
  • Book Chapter
  • Citations16

Support and Centrality: Learning Weights for Knowledge Graph Embedding Models

  • Jan 01, 2018
  • Gengchen Mai +2
  • Conference Article
  • Citations7

LAUREN - Knowledge Graph Summarization for Question Answering

  • Jan 01, 2021
  • Rricha Jalota +3
  • Conference Article

Uncertainty-Aware Dynamic Knowledge Graphs for Reliable Question Answering

  • Nov 12, 2025
  • Yu Takahashi +8
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.