Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models

TL;DR

This paper introduces KG-CoI, a system that enhances scientific hypothesis generation by grounding large language models with external knowledge graphs, improving accuracy and reducing hallucinations in generated hypotheses.

Contribution

The paper presents KG-CoI, a novel framework that integrates structured knowledge graphs into LLMs to improve hypothesis accuracy and mitigate hallucinations in scientific research.

Findings

KG-CoI improves hypothesis accuracy over baseline models.

The system reduces hallucinations in reasoning chains.

Experimental results validate the effectiveness of knowledge grounding.

Abstract

Large language models (LLMs) have demonstrated remarkable capabilities in various scientific domains, from natural language processing to complex problem-solving tasks. Their ability to understand and generate human-like text has opened up new possibilities for advancing scientific research, enabling tasks such as data analysis, literature review, and even experimental design. One of the most promising applications of LLMs in this context is hypothesis generation, where they can identify novel research directions by analyzing existing knowledge. However, despite their potential, LLMs are prone to generating ``hallucinations'', outputs that are plausible-sounding but factually incorrect. Such a problem presents significant challenges in scientific fields that demand rigorous accuracy and verifiability, potentially leading to erroneous or misleading conclusions. To overcome these challenges, we propose KG-CoI (Knowledge Grounded Chain of Ideas), a novel system that enhances LLM hypothesis generation by integrating external, structured knowledge from knowledge graphs (KGs). KG-CoI guides LLMs through a structured reasoning process, organizing their output as a chain of ideas (CoI), and includes a KG-supported module for the detection of hallucinations. With experiments on our newly constructed hypothesis generation dataset, we demonstrate that KG-CoI not only improves the accuracy of LLM-generated hypotheses but also reduces the hallucination in their reasoning chains, highlighting its effectiveness in advancing real-world scientific research.