# MapperGPT: Large Language Models for Linking and Mapping Entities

arXiv: https://arxiv.org/abs/2310.03666 · HTML: https://mlsanity.com/paper/2310.03666/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 5 Oct 2023.

## Builds on (most cited first, 6 of 6)

- [Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning](https://mlsanity.com/paper/2304.02711/) (2023)
- [Exploring Large Language Models for Ontology Alignment](https://mlsanity.com/paper/2309.07172/) (2023)
- [A Simple Standard for Sharing Ontological Mappings (SSSOM)](https://mlsanity.com/paper/2112.07051/) (2021)
- [Ontology Alignment in the Biomedical Domain Using Entity Definitions and Context](https://mlsanity.com/paper/1806.07976/) (2018)
- [VeeAlign: Multifaceted Context Representation using Dual Attention for Ontology Alignment](https://mlsanity.com/paper/2102.04081/) (2021)
- [Truveta Mapper: A Zero-shot Ontology Alignment Framework](https://mlsanity.com/paper/2301.09767/) (2023)

## Built on by (most cited first, 2 of 2)

- [Generalizable and Scalable Multistage Biomedical Concept Normalization Leveraging Large Language Models](https://mlsanity.com/paper/2405.15122/) (2024)
- [Exploring a Large Language Model for Transforming Taxonomic Data into OWL: Lessons Learned and Implications for Ontology Development](https://mlsanity.com/paper/2504.18651/) (2025)

## Abstract (arXiv)

Aligning terminological resources, including ontologies, controlled vocabularies, taxonomies, and value sets is a critical part of data integration in many domains such as healthcare, chemistry, and biomedical research. Entity mapping is the process of determining correspondences between entities across these resources, such as gene identifiers, disease concepts, or chemical entity identifiers. Many tools have been developed to compute such mappings based on common structural features and lexical information such as labels and synonyms. Lexical approaches in particular often provide very high recall, but low precision, due to lexical ambiguity. As a consequence of this, mapping efforts often resort to a labor intensive manual mapping refinement through a human curator. Large Language Models (LLMs), such as the ones employed by ChatGPT, have generalizable abilities to perform a wide range of tasks, including question-answering and information extraction. Here we present MapperGPT, an approach that uses LLMs to review and refine mapping relationships as a post-processing step, in concert with existing high-recall methods that are based on lexical and structural heuristics. We evaluated MapperGPT on a series of alignment tasks from different domains, including anatomy, developmental biology, and renal diseases. We devised a collection of tasks that are designed to be particularly challenging for lexical methods. We show that when used in combination with high-recall methods, MapperGPT can provide a substantial improvement in accuracy, beating state-of-the-art (SOTA) methods such as LogMap.