mlsanityData to 7 Oct 2026

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

arXiv 2406.11460 ↗First posted 17 Jun 2024cs.CL cs.AIcited by 16

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

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 noises 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 TRACE. 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 an 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.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 34 of its 44 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

34 of 44 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs17 Feb
  2. 2024Large Language Models Can Learn Temporal Reasoning12 Jan
  3. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning2 Oct
  4. 2023Single Sequence Prediction over Reasoning Graphs for Multi-hop QA1 Jul
  5. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec
  6. 2022UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph2 Dec

Other references · 28

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  7. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  11. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
16 more
  1. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  2. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  3. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  4. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  5. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  6. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 271
  7. 2023ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPTcited by 250
  8. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 194
  9. 2020How Context Affects Language Models' Factual Predictionscited by 181
  10. 2023Unified Demonstration Retriever for In-Context Learningcited by 141
  11. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 116
  12. 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
  13. 2019Knowledge Guided Text Retrieval and Reading for Open Domain Question Answeringcited by 59
  14. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 55
  15. 2022Modeling Multi-hop Question Answering as Single Sequence Predictioncited by 21
  16. 2024TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphscited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 9.

16 papers.

Sort:

By area:

  1. 2024On the Structural Memory of LLM Agentscited by 37
  2. 2024GeAR: Graph-enhanced Agent for Retrieval-augmented Generationcited by 17
  3. 2026SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Executioncited by 8
  4. 2026Procedural Knowledge at Scale Improves Reasoningcited by 7
  5. 2025Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metricscited by 4
  6. 2026NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chainscited by 3
  7. 2025Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layerscited by 2
  8. 2026RAG over Thinking Traces Can Improve Reasoning Taskscited by 2
  9. 2025Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimizationcited by 1
  10. 2026CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answeringcited by 1
  11. 2026TRACE: Tourism Recommendation with Accountable Citation Evidencecited by 1
  12. 2026Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generationcited by 1
4 more
  1. 2025KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAGcited by 0
  2. 2025Improving LLM's Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymizationcited by 0
  3. 2026AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interactioncited by 0
  4. 2026NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  2. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
  3. 2025GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation
  4. 2025Knowledge Graph-extended Retrieval Augmented Generation for Question Answering
  5. 2025Multi-hop Reasoning via Early Knowledge Alignment
  6. 2026D2F-ReAG: Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation
  7. 2025KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
  8. 2025SUBQRAG: Sub-Question Driven Dynamic Graph RAG