HypoChainer: A Collaborative System Combining LLMs and Knowledge Graphs for Hypothesis-Driven Scientific Discovery

HypoChainer: совместная система, объединяющая большие языковые модели и графы знаний для научных открытий на основе гипотез
Haoran Jiang, Shaohan Shi, Yunjie Yao, Chang Jiang, Quan Li
2025-12-03

HypoChainergraph neural networksknowledge graphslarge language modelsretrieval-augmented generation
Modern scientific discovery faces challenges in integrating the rapidly expanding and diverse knowledge required for exploring novel knowledge in biology. While traditional hypothesis-driven research has proven effective, it is constrained by human cognitive limitations, knowledge complexity, and the high costs of trial-and-error experimentation. Deep learning models, particularly graph neural networks (GNNs), have accelerated scientific progress. However, the vast predictions generated make manual selection for experimental validation impractical. Attempts to leverage large language models (LLMs) for filtering predictions and generating novel hypotheses have been impeded by issues such as hallucinations and the lack of structured knowledge grounding, which undermine their reliability. To address these challenges, we propose HypoChainer, a collaborative visualization framework that integrates human expertise, LLM-driven reasoning, and knowledge graphs (KGs) to enhance scientific discovery visually. HypoChainer operates through three key stages: (1) Contextual Exploration: Domain experts employ retrieval-augmented LLMs (RAGs) and visualizations to extract insights and research focuses from vast GNN predictions, supplemented by interactive explanations for in-depth understanding; (2) Hypothesis Construction: Experts iteratively explore the KG information relevant to the predictions and hypothesis-aligned entities, gaining knowledge and insights while refining the hypothesis through suggestions from LLMs; and (3) Validation Selection: Predictions are prioritized based on the refined hypothesis chains and KG-supported evidence, identifying high-priority candidates for validation. The hypothesis chains are further optimized through visual analytics of the retrieval results. We evaluated the effectiveness of HypoChainer in hypothesis construction and scientific discovery through a case study and expert interviews.
1
A case study and expert interviews evaluated HypoChainer’s effectiveness for hypothesis construction and scientific discovery.
2
Experts refine hypothesis chains by interactively exploring KG entities, visualized retrieval results, and LLM-generated suggestions.
3
HypoChainer integrates human expertise, retrieval-augmented LLM reasoning, knowledge graphs, and visualization for hypothesis-driven scientific discovery.
4
HypoChainer uses three stages: contextual exploration of GNN predictions, iterative hypothesis construction, and evidence-based validation candidate selection.
5
The framework addresses LLM hallucinations and unstructured knowledge limitations by grounding hypothesis generation and prediction filtering in knowledge graphs.

biology-focused scientific discovery involving GNN predictions, LLMs, and knowledge graphs

human–LLM collaborative construction, refinement, and validation prioritization of hypothesis chains grounded in knowledge-graph evidence

Publication Details
Publication Date
2025-12-03
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Haoran Jiang
Shaohan Shi
Yunjie Yao
Chang Jiang
Quan Li
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%