# Struct-X: Enhancing Large Language Models Reasoning with Structured Data

arXiv: https://arxiv.org/abs/2407.12522 · HTML: https://mlsanity.com/paper/2407.12522/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 13 of its 56 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 13 of 13)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [StructGPT: A General Framework for Large Language Model to Reason over Structured Data](https://mlsanity.com/paper/2305.09645/) (2023)
- [Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs](https://mlsanity.com/paper/2307.03393/) (2023)
- [LocalViT: Analyzing Locality in Vision Transformers](https://mlsanity.com/paper/2104.05707/) (2021)
- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [Does Synthetic Data Generation of LLMs Help Clinical Text Mining?](https://mlsanity.com/paper/2303.04360/) (2023)
- [Internet-augmented language models through few-shot prompting for open-domain question answering](https://mlsanity.com/paper/2203.05115/) (2022)
- [GraphLLM: Boosting Graph Reasoning Ability of Large Language Model](https://mlsanity.com/paper/2310.05845/) (2023)
- [Making Large Language Models Perform Better in Knowledge Graph Completion](https://mlsanity.com/paper/2310.06671/) (2023)
- [TRUE: Re-evaluating Factual Consistency Evaluation](https://mlsanity.com/paper/2204.04991/) (2022)

## Built on by (most cited first, 11 of 11)

- [HyperG: Hypergraph-Enhanced LLMs for Structured Knowledge](https://mlsanity.com/paper/2502.18125/) (2025)
- [Hybrid Graphs for Table-and-Text based Question Answering using LLMs](https://mlsanity.com/paper/2501.17767/) (2025)
- [RePanda: Pandas-powered Tabular Verification and Reasoning](https://mlsanity.com/paper/2503.11921/) (2025)
- [The Hidden Structure -- Improving Legal Document Understanding Through Explicit Text Formatting](https://mlsanity.com/paper/2505.12837/) (2025)
- [Integrating Expert Knowledge into Logical Programs via LLMs](https://mlsanity.com/paper/2502.12275/) (2025)
- [Heterogeneous Scientific Foundation Model Collaboration](https://mlsanity.com/paper/2604.27351/) (2026)
- [Structure First, Reason Next: Enhancing a Large Language Model using Knowledge Graph for Numerical Reasoning in Financial Documents](https://mlsanity.com/paper/2601.07754/) (2026)
- [Reviewing the Reviewer: Graph-Enhanced LLMs for E-commerce Appeal Adjudication](https://mlsanity.com/paper/2603.19267/) (2026)
- [SRAG: RAG with Structured Data Improves Vector Retrieval](https://mlsanity.com/paper/2603.26670/) (2026)
- [MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration](https://mlsanity.com/paper/2605.25030/) (2026)
- [CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning](https://mlsanity.com/paper/2606.02170/) (2026)

## Abstract (arXiv)

Structured data, rich in logical and relational information, has the potential to enhance the reasoning abilities of large language models (LLMs). Still, its integration poses a challenge due to the risk of overwhelming LLMs with excessive tokens and irrelevant context information. To address this, we propose Struct-X, a novel framework that operates through five key phases: ``read-model-fill-reflect-reason'' efficiently enabling LLMs to utilize structured data. It begins by encoding structured data into a topological space using graph embeddings, followed by filling in missing entity information with knowledge retrieval modules, and filtering out irrelevant tokens via a self-supervised module. The final phase involves constructing a topological network with selected tokens to further reduce the total token length for more effective LLM inference. Additionally, Struct-X includes an Auxiliary Module trained to generate prompts, aiding LLMs in analyzing structured data. Extensive experiments on benchmarks, including the knowledge graph question-answer task and the long document reading comprehension task, show that Struct-X notably improves LLM reasoning, demonstrating the effectiveness of structured data augmentation in improving LLM inference with complex input context.