Structured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning

Abstract

Creating knowledge bases and ontologies is a time consuming task that relies on a manual curation. AI/NLP approaches can assist expert curators in populating these knowledge bases, but current approaches rely on extensive training data, and are not able to populate arbitrary complex nested knowledge schemas. Here we present Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES), a Knowledge Extraction approach that relies on the ability of Large Language Models (LLMs) to perform zero-shot learning (ZSL) and general-purpose query answering from flexible prompts and return information conforming to a specified schema. Given a detailed, user-defined knowledge schema and an input text, SPIRES recursively performs prompt interrogation against GPT-3+ to obtain a set of responses matching the provided schema. SPIRES uses existing ontologies and vocabularies to provide identifiers for all matched elements. We present examples of use of SPIRES in different domains, including extraction of food recipes, multi-species cellular signaling pathways, disease treatments, multi-step drug mechanisms, and chemical to disease causation graphs. Current SPIRES accuracy is comparable to the mid-range of existing Relation Extraction (RE) methods, but has the advantage of easy customization, flexibility, and, crucially, the ability to perform new tasks in the absence of any training data. This method supports a general strategy of leveraging the language interpreting capabilities of LLMs to assemble knowledge bases, assisting manual knowledge curation and acquisition while supporting validation with publicly-available databases and ontologies external to the LLM. SPIRES is available as part of the open source OntoGPT package: https://github.com/ monarch-initiative/ontogpt.

Updated 2023-12-22

References in corpus (1)

• BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining

Cited by in corpus (14)

• Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health
• ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language Model
• Evaluation of large language models for discovery of gene set function
• Construction of Knowledge Graphs: State and Challenges
• Dynamic Retrieval Augmented Generation of Ontologies using Artificial Intelligence (DRAGON-AI)
• Towards Next-Generation Urban Decision Support Systems through AI-Powered Construction of Scientific Ontology using Large Language Models -- A Case in Optimizing Intermodal Freight Transportation
• Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models
• LinkML: An Open Data Modeling Framework
• The Vertebrate Breed Ontology: Towards Effective Breed Data Standardization
• Computational strategies for cross-species knowledge transfer
• Overcoming the Generalization Limits of SLM Finetuning for Shape-Based Extraction of Datatype and Object Properties
• The Open Syndrome Definition
• Flexible metadata harvesting for ecology using large language models
• Rosetta Statements: Simplifying FAIR Knowledge Graph Construction with a User-Centered Approach