# PromptLink: Leveraging Large Language Models for Cross-Source Biomedical Concept Linking

arXiv: https://arxiv.org/abs/2405.07500 · HTML: https://mlsanity.com/paper/2405.07500/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 13 May 2024.

## Builds on (most cited first, 18 of 18)

- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Text and Code Embeddings by Contrastive Pre-Training](https://mlsanity.com/paper/2201.10005/) (2022)
- [How Language Model Hallucinations Can Snowball](https://mlsanity.com/paper/2305.13534/) (2023)
- [Knowledge Enhanced Contextual Word Representations](https://mlsanity.com/paper/1909.04164/) (2019)
- [Bilinear Attention Networks](https://mlsanity.com/paper/1805.07932/) (2018)
- [Self-Alignment Pretraining for Biomedical Entity Representations](https://mlsanity.com/paper/2010.11784/) (2020)
- [Pre-trained Language Models in Biomedical Domain: A Systematic Survey](https://mlsanity.com/paper/2110.05006/) (2021)
- [SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs](https://mlsanity.com/paper/2203.01044/) (2022)
- [Knowledge-Rich Self-Supervision for Biomedical Entity Linking](https://mlsanity.com/paper/2112.07887/) (2021)
- [On the Effectiveness of Compact Biomedical Transformers](https://mlsanity.com/paper/2209.03182/) (2022)
- [HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting](https://mlsanity.com/paper/2304.05973/) (2023)
- [Exploring the In-context Learning Ability of Large Language Model for Biomedical Concept Linking](https://mlsanity.com/paper/2307.01137/) (2023)

## Built on by (most cited first, 15 of 15)

- [KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs](https://mlsanity.com/paper/2507.02773/) (2025)
- [HypKG: Hypergraph-based Knowledge Graph Contextualization for Precision Healthcare](https://mlsanity.com/paper/2507.19726/) (2025)
- [Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes](https://mlsanity.com/paper/2511.16548/) (2025)
- [Towards Automatic Evaluation and Selection of PHI De-identification Models via Multi-Agent Collaboration](https://mlsanity.com/paper/2510.16194/) (2025)
- [EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs](https://mlsanity.com/paper/2605.30637/) (2026)
- [CDE-Mapper: Using Retrieval-Augmented Language Models for Linking Clinical Data Elements to Controlled Vocabularies](https://mlsanity.com/paper/2505.04365/) (2025)
- [LLM-MINE: Large Language Model based Alzheimer's Disease and Related Dementias Phenotypes Mining from Clinical Notes](https://mlsanity.com/paper/2603.13673/) (2026)
- [GIP-RAG: An Evidence-Grounded Retrieval-Augmented Framework for Interpretable Gene Interaction and Pathway Impact Analysis](https://mlsanity.com/paper/2603.20321/) (2026)
- [BeLink: Biomedical Entity Linking Meets Generative Re-Ranking](https://mlsanity.com/paper/2605.22501/) (2026)
- [Evaluating the Impact of Lab Test Results on Large Language Models Generated Differential Diagnoses from Clinical Case Vignettes](https://mlsanity.com/paper/2411.02523/) (2024)
- [MIRAGE: Knowledge Graph-Guided Cross-Cohort MRI Synthesis for Alzheimer's Disease Prediction](https://mlsanity.com/paper/2603.02434/) (2026)
- [Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training](https://mlsanity.com/paper/2603.13297/) (2026)
- [LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking](https://mlsanity.com/paper/2605.13451/) (2026)
- [BioELX: Context-Aware Cross-lingual Biomedical Entity Linking without Task-Specific Supervision](https://mlsanity.com/paper/2605.27380/) (2026)
- [LLMBDC: Language Model for Biological Domains Oriented Clustering of Gene Ontology](https://mlsanity.com/paper/2608.00099/) (2026)

## Abstract (arXiv)

Linking (aligning) biomedical concepts across diverse data sources enables various integrative analyses, but it is challenging due to the discrepancies in concept naming conventions. Various strategies have been developed to overcome this challenge, such as those based on string-matching rules, manually crafted thesauri, and machine learning models. However, these methods are constrained by limited prior biomedical knowledge and can hardly generalize beyond the limited amounts of rules, thesauri, or training samples. Recently, large language models (LLMs) have exhibited impressive results in diverse biomedical NLP tasks due to their unprecedentedly rich prior knowledge and strong zero-shot prediction abilities. However, LLMs suffer from issues including high costs, limited context length, and unreliable predictions. In this research, we propose PromptLink, a novel biomedical concept linking framework that leverages LLMs. It first employs a biomedical-specialized pre-trained language model to generate candidate concepts that can fit in the LLM context windows. Then it utilizes an LLM to link concepts through two-stage prompts, where the first-stage prompt aims to elicit the biomedical prior knowledge from the LLM for the concept linking task and the second-stage prompt enforces the LLM to reflect on its own predictions to further enhance their reliability. Empirical results on the concept linking task between two EHR datasets and an external biomedical KG demonstrate the effectiveness of PromptLink. Furthermore, PromptLink is a generic framework without reliance on additional prior knowledge, context, or training data, making it well-suited for concept linking across various types of data sources. The source code is available at https://github.com/constantjxyz/PromptLink.