Structured Prompt Interrogation and Recursive Extraction of Semantics (SPIRES): a method for populating knowledge bases using zero-shot learning
[1];
[1];
[2];
[1];
[1];
[3];
[4];
[1];
[1];
[5];
[6];
[1]
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Maastricht University (Netherlands)
- Semanticly, Athens (Greece)
- Robert Bosch LLC, Sunnyvale, CA (United States)
- University of Colorado, Aurora, CO (United States). Anschutz Medical Campus
- Berlin Institute of Health at Charité (Germany)
Creating knowledge bases and ontologies is a time consuming task that relies on 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 arbitrarily 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 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 an LLM to obtain a set of responses matching the provided schema. SPIRES uses existing ontologies and vocabularies to provide identifiers for matched elements. We present examples of applying SPIRES in different domains, including extraction of food recipes, multi species cellular signaling pathways, disease treatments, multi-step drug mechanisms, and chemical to disease relationships. Current SPIRES accuracy is comparable to the mid-range of existing Relation Extraction methods, but greatly surpasses an LLM’s native capability of grounding entities with unique identifiers. SPIRES has the advantage of easy customization, flexibility, and, crucially, the ability to perform new tasks in the absence of any new 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.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Basic Energy Sciences (BES); National Institutes of Health (NIH); USDOE
- Grant/Contract Number:
- AC02-05CH11231; RM1 HG010860; R24 OD011883; AC0205CH11231
- OSTI ID:
- 2322444
- Alternate ID(s):
- OSTI ID: 2426861
- Journal Information:
- Bioinformatics, Vol. 40, Issue 3; ISSN 1367-4803
- Publisher:
- Oxford University PressCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
An evaluation of GPT models for phenotype concept recognition
The Artificial Intelligence Ontology: LLM-Assisted Construction of AI Concept Hierarchies