mlsanityData to 14 Oct 2026

Follow the Path: Reasoning over Knowledge Graph Paths to Improve Large Language Model Factuality

arXiv 2505.11140 ↗First posted 16 May 2025cs.CL cs.AIcited by 1

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

Abstract (arXiv)

We introduce fs1, a simple yet effective method that improves the factuality of reasoning traces by collecting them from large reasoning models and grounding them in knowledge graph (KG) paths. We fine-tune eight instruction-tuned Large Language Models (LLMs) on 3.9K factually grounded reasoning traces and rigorously evaluate them on six complex open-domain question-answering (QA) benchmarks encompassing 23.9K questions. Our results demonstrate that our fs1-tuned model consistently outperforms instruction-tuned counterparts with parallel sampling by 6-14 absolute points (pass@16). Our detailed analysis shows that fs1 considerably improves model performance over more complex questions (requiring 3 or more hops on KG paths) and numerical answer types compared to the baselines. Furthermore, in single-pass inference, we notice that smaller LLMs show the most improvements. While prior works demonstrate the effectiveness of reasoning traces primarily in the STEM domains, our work shows strong evidence that anchoring reasoning to factual KG paths is a critical step in transforming LLMs for reliable knowledge-intensive tasks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 62 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

27 of 62 references.

References · 27

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  4. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  5. 2025s1: Simple test-time scalingcited by 1,341
  6. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  7. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  8. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
  9. 2024Measuring short-form factuality in large language modelscited by 373
  10. 2024Training Software Engineering Agents and Verifiers with SWE-Gymcited by 336
  11. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Modelscited by 290
  12. 2025A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?cited by 223
15 more
  1. 2025Reasoning Models Can Be Effective Without Thinkingcited by 187
  2. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 164
  3. 2019On the Measure of Intelligencecited by 144
  4. 2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!cited by 132
  5. 2025MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphscited by 110
  6. 2025T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scalingcited by 77
  7. 2023Rewarding Chatbots for Real-World Engagement with Millions of Userscited by 59
  8. 2025Evolving Deeper LLM Thinkingcited by 58
  9. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 56
  10. 2024The Limits of Inference Scaling Through Resamplingcited by 53
  11. 2025m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Modelscited by 46
  12. 2024The Larger the Better? Improved LLM Code-Generation via Budget Reallocationcited by 43
  13. 2024A Simple Model of Inference Scaling Lawscited by 36
  14. 2025Z1: Efficient Test-time Scaling with Codecited by 35
  15. 2025Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answeringcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Peak-Then-Collapse and the Four Interface Channels of Knowledge-Graph Tool Usecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
  2. 2024Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning
  3. 2024Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering
  4. 2025Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
  5. 2025KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration
  6. 2022Faithful Reasoning Using Large Language Models
  7. 2024Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models
  8. 2024KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model's Reasoning Path Aggregation