# Biomedical Hypothesis Explainability with Graph-Based Context Retrieval

arXiv: https://arxiv.org/abs/2511.05498 · HTML: https://mlsanity.com/paper/2511.05498/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 59 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval](https://mlsanity.com/paper/2307.00589/) (2023)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [SciFive: a text-to-text transformer model for biomedical literature](https://mlsanity.com/paper/2106.03598/) (2021)
- [Neighborhood Contrastive Learning for Scientific Document Representations with Citation Embeddings](https://mlsanity.com/paper/2202.06671/) (2022)
- [Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions](https://mlsanity.com/paper/2408.00727/) (2024)
- [Biomedical Question Answering: A Survey of Approaches and Challenges](https://mlsanity.com/paper/2102.05281/) (2021)
- [Biomedical knowledge graph-optimized prompt generation for large language models](https://mlsanity.com/paper/2311.17330/) (2023)
- [BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine](https://mlsanity.com/paper/2405.00465/) (2024)
- [AGATHA: Automatic Graph-mining And Transformer based Hypothesis generation Approach](https://mlsanity.com/paper/2002.05635/) (2020)
- [Can ChatGPT be used to generate scientific hypotheses?](https://mlsanity.com/paper/2304.12208/) (2023)
- [MOLIERE: Automatic Biomedical Hypothesis Generation System](https://mlsanity.com/paper/1702.06176/) (2017)
- [Large-Scale Validation of Hypothesis Generation Systems via Candidate Ranking](https://mlsanity.com/paper/1802.03793/) (2018)
- [CBAG: Conditional Biomedical Abstract Generation](https://mlsanity.com/paper/2002.05637/) (2020)
- [Explainable Biomedical Hypothesis Generation via Retrieval Augmented Generation enabled Large Language Models](https://mlsanity.com/paper/2407.12888/) (2024)
- [Developing a Knowledge Graph Framework for Pharmacokinetic Natural Product-Drug Interactions](https://mlsanity.com/paper/2209.11950/) (2022)
- [Automated Explanation Selection for Scientific Discovery](https://mlsanity.com/paper/2407.17454/) (2024)

## Abstract (arXiv)

We introduce an explainability method for biomedical hypothesis generation systems, built on top of the novel Hypothesis Generation Context Retriever 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 with contextual evidence using published scientific literature. We also propose a novel feedback loop approach, which iteratively identifies and corrects flawed parts of LLM-generated explanations, refining both the evidence paths and supporting context. We demonstrate the performance of our method with multiple large language models and evaluate the explanation and context retrieval quality through both expert-curated assessment and large-scale automated analysis. Our code is available at: https://github.com/IlyaTyagin/HGCR.