VerifAI is an open-source biomedical QA system that decomposes generated answers into claims and verifies them with a fine-tuned NLI engine to reduce hallucinations and provide traceable citations.
Gautier Izacard and Edouard Grave
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Cross-encoder reranking delivers the highest composite score (0.827) and contextual precision (0.852) among five retrieval strategies in biomedical RAG, with all retrieval conditions far outperforming a no-context baseline on answer relevancy.
Corpus aggregation boosts retrieval quality in biomedical settings, with MedRAG/pubmed as the strongest single corpus under HNSW graph indexing and FAISS for speed-efficiency balance.
citing papers explorer
-
VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering
VerifAI is an open-source biomedical QA system that decomposes generated answers into claims and verifies them with a fine-tuned NLI engine to reduce hallucinations and provide traceable citations.
-
Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study
Cross-encoder reranking delivers the highest composite score (0.827) and contextual precision (0.852) among five retrieval strategies in biomedical RAG, with all retrieval conditions far outperforming a no-context baseline on answer relevancy.
-
A Systematic Study of Biomedical Retrieval Pipeline Trade-offs in Performance and Efficiency
Corpus aggregation boosts retrieval quality in biomedical settings, with MedRAG/pubmed as the strongest single corpus under HNSW graph indexing and FAISS for speed-efficiency balance.