# Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge

arXiv: https://arxiv.org/abs/2402.12352 · HTML: https://mlsanity.com/paper/2402.12352/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 33 of its 39 references that are in the map.
- First posted on arXiv 19 Feb 2024.

## Placed in

- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 30 of 33)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing](https://mlsanity.com/paper/1902.07669/) (2019)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers](https://mlsanity.com/paper/2305.07185/) (2023)
- [Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering](https://mlsanity.com/paper/2005.00646/) (2020)
- [Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization](https://mlsanity.com/paper/2302.08081/) (2023)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [BioRED: A Rich Biomedical Relation Extraction Dataset](https://mlsanity.com/paper/2204.04263/) (2022)
- [Barack's Wife Hillary: Using Knowledge-Graphs for Fact-Aware Language Modeling](https://mlsanity.com/paper/1906.07241/) (2019)
- [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2106.10502/) (2021)
- [FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge](https://mlsanity.com/paper/2305.08281/) (2023)
- [RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding](https://mlsanity.com/paper/2212.01588/) (2022)
- [From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer](https://mlsanity.com/paper/2202.02113/) (2022)
- [PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs](https://mlsanity.com/paper/2305.12392/) (2023)
- [BERN2: an advanced neural biomedical named entity recognition and normalization tool](https://mlsanity.com/paper/2201.02080/) (2022)
- [JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering](https://mlsanity.com/paper/2112.02732/) (2021)
- [The Current State of Summarization](https://mlsanity.com/paper/2305.04853/) (2023)

## Built on by (most cited first, 20 of 20)

- [Graph Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2408.08921/) (2024)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [AI and the Problem of Knowledge Collapse](https://mlsanity.com/paper/2404.03502/) (2024)
- [KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG](https://mlsanity.com/paper/2502.09304/) (2025)
- [Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models](https://mlsanity.com/paper/2411.02382/) (2024)
- [Multi-Head RAG: Solving Multi-Aspect Problems with LLMs](https://mlsanity.com/paper/2406.05085/) (2024)
- [Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey](https://mlsanity.com/paper/2504.10499/) (2025)
- [Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation](https://mlsanity.com/paper/2407.12216/) (2024)
- [Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases](https://mlsanity.com/paper/2502.20317/) (2025)
- [End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning](https://mlsanity.com/paper/2508.15746/) (2025)
- [Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination](https://mlsanity.com/paper/2410.17783/) (2024)
- [How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback](https://mlsanity.com/paper/2501.15378/) (2025)
- [PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR](https://mlsanity.com/paper/2601.18207/) (2026)
- [How to Make LMs Strong Node Classifiers?](https://mlsanity.com/paper/2410.02296/) (2024)
- [Can We Edit LLMs for Long-Tail Biomedical Knowledge?](https://mlsanity.com/paper/2504.10421/) (2025)
- [Right Answer at the Right Time - Temporal Retrieval-Augmented Generation via Graph Summarization](https://mlsanity.com/paper/2510.16715/) (2025)
- [G-RAG: Knowledge Expansion in Material Science](https://mlsanity.com/paper/2411.14592/) (2024)
- [GraphSeek: Next-Generation Graph Analytics with LLMs](https://mlsanity.com/paper/2602.11052/) (2026)
- [Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.24120/) (2025)
- [MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistry](https://mlsanity.com/paper/2608.28315/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are transforming the way information is retrieved with vast amounts of knowledge being summarized and presented via natural language conversations. Yet, LLMs are prone to highlight the most frequently seen pieces of information from the training set and to neglect the rare ones. In the field of biomedical research, latest discoveries are key to academic and industrial actors and are obscured by the abundance of an ever-increasing literature corpus (the information overload problem). Surfacing new associations between biomedical entities, e.g., drugs, genes, diseases, with LLMs becomes a challenge of capturing the long-tail knowledge of the biomedical scientific production. To overcome this challenge, Retrieval Augmented Generation (RAG) has been proposed to alleviate some of the shortcomings of LLMs by augmenting the prompts with context retrieved from external datasets. RAG methods typically select the context via maximum similarity search over text embeddings. In this study, we show that RAG methods leave out a significant proportion of relevant information due to clusters of over-represented concepts in the biomedical literature. We introduce a novel information-retrieval method that leverages a knowledge graph to downsample these clusters and mitigate the information overload problem. Its retrieval performance is about twice better than embedding similarity alternatives on both precision and recall. Finally, we demonstrate that both embedding similarity and knowledge graph retrieval methods can be advantageously combined into a hybrid model that outperforms both, enabling potential improvements to biomedical question-answering models.