{"doi":"10.1145/3698587.3701384","title":"MetaphorPrompt - An Analogical Reasoning Approach for Extracting Causal Links from Biological Text","abstract":"In recent years, Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP), offering significant improvements for extracting complex information from biomedical literature. Our research introduces a novel metaphor-based approach, MetaphorPrompt, to enhance the accuracy of extracting molecular regulatory pathways (MRPs) from biomedical texts. This method employs LLMs such as GPT4 to develop metaphors that map biological processes onto familiar, real-world scenarios, facilitating a better understanding and extracting causal events in MRPs. MetaphorPrompt is tested using the reguloGPT dataset and compared to a baseline method (without metaphors) and reguloGPT's best prompt. Test results demonstrate improved precision, recall, and F1 scores in node and edge prediction of causal event links through analogical reasoning. The effect of in-context learning (ICL) in MetaphorPrompt is investigated, and it is found that analogical reasoning offers significant improvements over ICL. This supports the claim that LLMs can perform novel problem-solving through analogical reasoning. This work paves the way for more intuitive and user-friendly representations of MRPs in biomedical data, ultimately contributing to advancements in biomedical NLP, knowledge graph construction, and effective applications of LLMs in novel problem-solving through analogical reasoning.","journal":null,"year":2024,"id":492639,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9573,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":238478,"name":"Yu‐Chiao Chiu","orcid":"0000-0003-1647-8634","position":1,"is_corresponding":false},{"id":238479,"name":"Yufei Huang","orcid":"0000-0001-6268-5357","position":2,"is_corresponding":false},{"id":1338877,"name":"Jianqiu Zhang","orcid":"0000-0002-4812-4403","position":3,"is_corresponding":false},{"id":1338876,"name":"Parth Patel","orcid":"0009-0002-5218-8714","position":0,"is_corresponding":true}],"reference_count":22,"raw_metadata":null,"created_at":"2026-07-19T02:08:56.210382Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}