Verif.ai: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answers
This addresses the need for trustworthy AI tools in scientific research where misinformation is unacceptable, though it appears incremental as it builds on existing retrieval and generation methods.
The authors tackled the problem of unreliable answers from generative AI in scientific contexts by developing Verif.ai, an open-source question-answering system that combines retrieval, generation with references, and verification to reduce hallucinations.
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.