# Causal Reasoning in Large Language Models: A Knowledge Graph Approach

arXiv: https://arxiv.org/abs/2410.11588 · HTML: https://mlsanity.com/paper/2410.11588/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 6 of its 16 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 6 of 6)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Knowledge Graph Prompting for Multi-Document Question Answering](https://mlsanity.com/paper/2308.11730/) (2023)
- [Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks](https://mlsanity.com/paper/2311.12786/) (2023)
- [Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2305.16582/) (2023)

## Built on by (most cited first, 9 of 9)

- [LLM-empowered knowledge graph construction: A survey](https://mlsanity.com/paper/2510.20345/) (2025)
- [LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding](https://mlsanity.com/paper/2510.07233/) (2025)
- [KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs](https://mlsanity.com/paper/2504.07087/) (2025)
- [R2-KG: General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2502.12767/) (2025)
- [TimeMKG: Knowledge-Infused Causal Reasoning for Multivariate Time Series Modeling](https://mlsanity.com/paper/2508.09630/) (2025)
- [CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs](https://mlsanity.com/paper/2602.08939/) (2026)
- [UniCode: Augmenting Evaluation for Code Reasoning](https://mlsanity.com/paper/2510.17868/) (2025)
- [Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models](https://mlsanity.com/paper/2601.00003/) (2025)
- [DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data](https://mlsanity.com/paper/2607.09348/) (2026)

## Abstract (arXiv)

Large language models (LLMs) typically improve performance by either retrieving semantically similar information, or enhancing reasoning abilities through structured prompts like chain-of-thought. While both strategies are considered crucial, it remains unclear which has a greater impact on model performance or whether a combination of both is necessary. This paper answers this question by proposing a knowledge graph (KG)-based random-walk reasoning approach that leverages causal relationships. We conduct experiments on the commonsense question answering task that is based on a KG. The KG inherently provides both relevant information, such as related entity keywords, and a reasoning structure through the connections between nodes. Experimental results show that the proposed KG-based random-walk reasoning method improves the reasoning ability and performance of LLMs. Interestingly, incorporating three seemingly irrelevant sentences into the query using KG-based random-walk reasoning enhances LLM performance, contrary to conventional wisdom. These findings suggest that integrating causal structures into prompts can significantly improve reasoning capabilities, providing new insights into the role of causality in optimizing LLM performance.