{"doi":"10.1101/2025.06.09.25329279","title":"Precision Grounding: Augmenting Large Language Models with Evidence-Based Databases for Trustworthy Genetic Variant Summarization","abstract":"Backgrounds: Accurate interpretation of genetic variants is critical for precision medicine. While large language models (LLMs) show promise for summarization, they are prone to hallucinations. In this study, we thus propose a novel approach named \"precision grounding\" that augments LLMs with a query tool that integrated evidence-based, variant-specific information to improve summarization accuracy. Methods: Unlike traditional RAG methods that retrieve information via document embeddings from a vector database, precision grounding uses a domain-specific query tool to access evidence-based databases with unique identifiers. For variant summarization, we developed CATT (https://shorturl.at/pw81X), an open-source tool integrating ClinGen, ClinVar, and GenCC data. Users can query and retrieve curated evidence via Variation IDs to ground LLM outputs. We compared our approach to web grounding-based RAG using 50 expert-selected variants. Results: GPT-4o was selected due to its good performance on our task during a pilot test. Using GPT-4o, we found our precision grounding approach outperformed web-search grounding, achieving significantly higher accuracy and completeness scores, which were based on a 5-point Likert-Scale of 4.76 (+0.74) and 4.94 (+0.84), respectively. Error analysis revealed that precision grounding reduced clinically significant hallucinations, such as incorrect pathogenicity classification and summarizing the wrong variant. Conclusion: Precision grounding approach outperformed web-search grounding for genetic variant summarization. Our open-source tool, CATT, enables integration of curated, domain-specific knowledge and reduces hallucinations in LLM outputs.","journal":"medRxiv","year":2025,"id":558227,"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":0.9533,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1458675,"name":"Anna Andrea Nagy","orcid":"0000-0001-7154-4548","position":1,"is_corresponding":false},{"id":972174,"name":"Michael Oates","orcid":"0000-0003-0131-2578","position":2,"is_corresponding":false},{"id":1458676,"name":"Yifei Wang","orcid":"0009-0009-1890-9232","position":3,"is_corresponding":false},{"id":919743,"name":"Xinyi Wang","orcid":"0000-0002-7389-6018","position":4,"is_corresponding":false},{"id":950486,"name":"Joseph M. Plasek","orcid":"0000-0002-9686-3876","position":5,"is_corresponding":false},{"id":596067,"name":"Samuel Aronson","orcid":"0000-0002-2490-6822","position":6,"is_corresponding":false},{"id":381639,"name":"Matthew S. Lebo","orcid":"0000-0002-9733-5207","position":7,"is_corresponding":false},{"id":1458677,"name":"Li Zhou","orcid":"0000-0002-2998-0300","position":8,"is_corresponding":false},{"id":432794,"name":"Xinsong Du","orcid":"0000-0003-3713-3264","position":0,"is_corresponding":true}],"reference_count":24,"raw_metadata":null,"created_at":"2026-07-19T02:55:25.969263Z","pmid":"40585076","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":[]}