Biomedical Hypothesis Explainability with Graph-Based Context Retrieval

Ilya Tyagin, Saeideh Valipour, Aliaksandra Sikirzhytskaya, Michael Shtutman, Ilya Safro
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

We introduce an explainability method for biomedical hypothesis generation systems, built on the the novel Hypothesis Generation Context Refiner framework. Our approach combines semantic graph-based retrieval, and relevant data-restrictive training to simulate real-world discovery constraints. Integrated with large language models (LLMs) via retrieval-augmented generation, the system explains hypotheses in contextual evidence using published scientific literature. We propose a novel feedback loop approach, which iteratively identifies and corrects flawed parts of LLM-generated explanations, refining both the evidence paths and supporting papers. We demonstrate the performance of our method with multiple large language models and evaluate explanation and context retrieval quality through both expert-curated assessment and large-scale automated analysis.\\{Reproducibility}: our code and data are available at [link will be added upon acceptance]

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-tyagin25a, title = {Biomedical Hypothesis Explainability with Graph-Based Context Retrieval}, author = {Tyagin, Ilya and Valipour, Saeideh and Sikirzhytskaya, Aliaksandra and Shtutman, Michael and Safro, Ilya}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/tyagin25a/tyagin25a.pdf}, url = {https://proceedings.mlr.press/v298/tyagin25a.html}, abstract = {We introduce an explainability method for biomedical hypothesis generation systems, built on the the novel Hypothesis Generation Context Refiner framework. Our approach combines semantic graph-based retrieval, and relevant data-restrictive training to simulate real-world discovery constraints. Integrated with large language models (LLMs) via retrieval-augmented generation, the system explains hypotheses in contextual evidence using published scientific literature. We propose a novel feedback loop approach, which iteratively identifies and corrects flawed parts of LLM-generated explanations, refining both the evidence paths and supporting papers. We demonstrate the performance of our method with multiple large language models and evaluate explanation and context retrieval quality through both expert-curated assessment and large-scale automated analysis.\\{Reproducibility}: our code and data are available at [link will be added upon acceptance]} }
Endnote
%0 Conference Paper %T Biomedical Hypothesis Explainability with Graph-Based Context Retrieval %A Ilya Tyagin %A Saeideh Valipour %A Aliaksandra Sikirzhytskaya %A Michael Shtutman %A Ilya Safro %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-tyagin25a %I PMLR %U https://proceedings.mlr.press/v298/tyagin25a.html %V 298 %X We introduce an explainability method for biomedical hypothesis generation systems, built on the the novel Hypothesis Generation Context Refiner framework. Our approach combines semantic graph-based retrieval, and relevant data-restrictive training to simulate real-world discovery constraints. Integrated with large language models (LLMs) via retrieval-augmented generation, the system explains hypotheses in contextual evidence using published scientific literature. We propose a novel feedback loop approach, which iteratively identifies and corrects flawed parts of LLM-generated explanations, refining both the evidence paths and supporting papers. We demonstrate the performance of our method with multiple large language models and evaluate explanation and context retrieval quality through both expert-curated assessment and large-scale automated analysis.\\{Reproducibility}: our code and data are available at [link will be added upon acceptance]
APA
Tyagin, I., Valipour, S., Sikirzhytskaya, A., Shtutman, M. & Safro, I.. (2025). Biomedical Hypothesis Explainability with Graph-Based Context Retrieval. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/tyagin25a.html.

Related Material