Graphical Reasoning: LLM-based Semi-Open Relation Extraction

Yicheng Tao, Yiqun Wang, Longju Bai
4/30/2024
cs.CLcs.AIcs.LG

No official code found. Best implementation: LongjuBai/EECS598_LLM_RelationExtraction (4 stars, last commit 2026-02-02).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

LongjuBai/EECS598_LLM_RelationExtractionCommunity100%
40Shell, PythonApr 3, 20248 months ago

Similar Papers

Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning

84% match2024

Bridging Generative and Discriminative Learning: Few-Shot Relation Extraction via Two-Stage Knowledge-Guided Pre-training

84% match1 repo72025

CPTuning: Contrastive Prompt Tuning for Generative Relation Extraction

83% match2025

Path-of-Thoughts: Extracting and Following Paths for Robust Relational Reasoning with Large Language Models

83% match2024

Graph-Augmented Relation Extraction Model with LLMs-Generated Support Document

83% match2024

A survey on cutting-edge relation extraction techniques based on language models

83% match2024

Cite this paper

@article{tao2024graphical,
  title  = {Graphical Reasoning: LLM-based Semi-Open Relation Extraction},
  author = {Yicheng Tao and Yiqun Wang and Longju Bai},
  year   = {2024},
  eprint = {2405.00216},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.00216v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.00216.svg)](https://codeofpaper.com/paper/2405.00216)

Discussion