# HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answering

arXiv: https://arxiv.org/abs/2501.01203 · HTML: https://mlsanity.com/paper/2501.01203/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2025.

## Built on by (most cited first, 5 of 5)

- [Choosing How to Remember: Adaptive Memory Structures for LLM Agents](https://mlsanity.com/paper/2602.14038/) (2026)
- [Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator](https://mlsanity.com/paper/2507.11810/) (2025)
- [MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs](https://mlsanity.com/paper/2510.14629/) (2025)
- [CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning](https://mlsanity.com/paper/2603.27685/) (2026)
- [Large language models for post-publication research evaluation: Evidence from expert recommendations and citation indicators](https://mlsanity.com/paper/2604.16387/) (2026)

## Abstract (arXiv)

Academic question answering (QA) in heterogeneous scholarly networks presents unique challenges requiring both structural understanding and interpretable reasoning. While graph neural networks (GNNs) capture structured graph information and large language models (LLMs) demonstrate strong capabilities in semantic comprehension, current approaches lack integration at the reasoning level. We propose HetGCoT, a framework enabling LLMs to effectively leverage and learn information from graphs to reason interpretable academic QA results. Our framework introduces three technical contributions: (1) a framework that transforms heterogeneous graph structural information into LLM-processable reasoning chains, (2) an adaptive metapath selection mechanism identifying relevant subgraphs for specific queries, and (3) a multi-step reasoning strategy systematically incorporating graph contexts into the reasoning process. Experiments on OpenAlex and DBLP datasets show our approach outperforms all sota baselines. The framework demonstrates adaptability across different LLM architectures and applicability to various scholarly question answering tasks.