# Graphical Reasoning: LLM-based Semi-Open Relation Extraction

arXiv: https://arxiv.org/abs/2405.00216 · HTML: https://mlsanity.com/paper/2405.00216/

## Key facts

- Cited by 4 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 2 of its 12 references that are in the map.
- First posted on arXiv 30 Apr 2024.

## Placed in

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

## Builds on (most cited first, 2 of 2)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Revisiting Large Language Models as Zero-shot Relation Extractors](https://mlsanity.com/paper/2310.05028/) (2023)

## Built on by (most cited first, 4 of 4)

- [GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases](https://mlsanity.com/paper/2605.30237/) (2026)
- [Can an LLM Induce a Graph? Investigating Memory Drift and Context Length](https://mlsanity.com/paper/2510.03611/) (2025)
- [Relation Extraction Across Entire Books to Reconstruct Community Networks: The AffilKG Datasets](https://mlsanity.com/paper/2505.10798/) (2025)
- [Relation as a Prior: A Novel Paradigm for LLM-based Document-level Relation Extraction](https://mlsanity.com/paper/2511.08143/) (2025)

## Abstract (arXiv)

This paper presents a comprehensive exploration of relation extraction utilizing advanced language models, specifically Chain of Thought (CoT) and Graphical Reasoning (GRE) techniques. We demonstrate how leveraging in-context learning with GPT-3.5 can significantly enhance the extraction process, particularly through detailed example-based reasoning. Additionally, we introduce a novel graphical reasoning approach that dissects relation extraction into sequential sub-tasks, improving precision and adaptability in processing complex relational data. Our experiments, conducted on multiple datasets, including manually annotated data, show considerable improvements in performance metrics, underscoring the effectiveness of our methodologies.