Verif.ai: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answers

TL;DR

Verif.ai is an open-source scientific question-answering system that combines retrieval, generative modeling, and verification to produce referenced, verifiable answers and reduce hallucinations in scientific contexts.

Contribution

The paper introduces a novel integrated system that combines retrieval, generative, and verification components for scientific QA with references and hallucination checks.

Findings

System effectively retrieves relevant scientific papers.

Generative model produces answers with references.

Verification engine reduces hallucinations.

Abstract

In this paper, we present the current progress of the project Verif.ai, an open-source scientific generative question-answering system with referenced and verified answers. The components of the system are (1) an information retrieval system combining semantic and lexical search techniques over scientific papers (PubMed), (2) a fine-tuned generative model (Mistral 7B) taking top answers and generating answers with references to the papers from which the claim was derived, and (3) a verification engine that cross-checks the generated claim and the abstract or paper from which the claim was derived, verifying whether there may have been any hallucinations in generating the claim. We are reinforcing the generative model by providing the abstract in context, but in addition, an independent set of methods and models are verifying the answer and checking for hallucinations. Therefore, we believe that by using our method, we can make scientists more productive, while building trust in the use of generative language models in scientific environments, where hallucinations and misinformation cannot be tolerated.