VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering
On the map: Retrieval-augmented generation → Medical and biomedical RAG
Abstract (arXiv)
We introduce VerifAI, an open-source expert system for biomedical question answering that integrates retrieval-augmented generation (RAG) with a novel post-hoc claim verification mechanism. Unlike standard RAG systems, VerifAI ensures factual consistency by decomposing generated answers into atomic claims and validating them against retrieved evidence using a fine-tuned natural language inference (NLI) engine. The system comprises three modular components: (1) a hybrid Information Retrieval (IR) module optimized for biomedical queries (MAP@10 of 42.7%), (2) a citation-aware Generative Component fine-tuned on a custom dataset to produce referenced answers, and (3) a Verification Component that detects hallucinations with state-of-the-art accuracy, outperforming GPT-4 on the HealthVer benchmark. Evaluations demonstrate that VerifAI significantly reduces hallucinated citations compared to zero-shot baselines and provides a transparent, verifiable lineage for every claim. The full pipeline, including code, models, and datasets, is open-sourced to facilitate reliable AI deployment in high-stakes domains.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 39 of its 67 references that are in the map. First posted on arXiv 16 Jan 2026.
Builds on
39 of 67 references.
Closest ancestors · 1
Same direction, newest first
Other references · 38
- 2023GPT-4 Technical Reportcited by 18,396
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
- 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
- 2022Survey of Hallucination in Natural Language Generationcited by 2,075
- 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
- 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
26 more
- 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
- 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
- 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 638
- 2023Enabling Large Language Models to Generate Text with Citationscited by 595
- 2020Fact or Fiction: Verifying Scientific Claimscited by 554
- 2022BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Miningcited by 538
- 2023Evaluating Verifiability in Generative Search Enginescited by 303
- 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
- 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
- 2024Corrective Retrieval Augmented Generationcited by 197
- 2024Long-form factuality in large language modelscited by 155
- 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 139
- 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 83
- 2023HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checkingcited by 35
- 2020Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approachcited by 32
- 2023Retrieving Supporting Evidence for Generative Question Answeringcited by 31
- 2022BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examplescited by 15
- 2024Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Modelscited by 15
- 2024Qibo: A Large Language Model for Traditional Chinese Medicinecited by 13
- 2024FACTOID: FACtual enTailment fOr hallucInation Detectioncited by 10
- 2024Improving Factuality with Explicit Working Memorycited by 10
- 2024HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluationcited by 6
- 2024How do you know that? Teaching Generative Language Models to Reference Answers to Biomedical Questionscited by 5
- 2024VERA: Validation and Enhancement for Retrieval Augmented systemscited by 2
- 2024ChatSOS: Vector Database Augmented Generative Question Answering Assistant in Safety Engineeringcited by 1
- 2025VERIRAG: A Post-Retrieval Auditing of Scientific Study Summariescited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026MedRAGChecker: Claim-Level Verification for Biomedical Retrieval-Augmented Generation
- 2025MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering
- 2026PubMed Reasoner: Dynamic Reasoning-based Retrieval for Evidence-Grounded Biomedical Question Answering
- 2024Scientific QA System with Verifiable Answers
- 2025Harnessing Collective Intelligence of LLMs for Robust Biomedical QA: A Multi-Model Approach
- 2025Improving Reliability and Explainability of Medical Question Answering through Atomic Fact Checking in Retrieval-Augmented LLMs
- 2025RAG-BioQA: A Retrieval-Augmented Generation Framework for Long-Form Biomedical Question Answering
- 2026When Retrieval Doesn't Help: A Large-Scale Study of Biomedical RAG