Home // INTERNET 2024, The Sixteenth International Conference on Evolving Internet // View article
Authors:
Miloš Košprdić
Adela Ljajić
Bojana Bašaragin
Darija Medvecki
Nikola Milošević
Keywords: question-answering; automatic referencing; generative search; large language models; natural language inference.
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.
Pages: 1 to 5
Copyright: Copyright (c) IARIA, 2024
Publication date: March 10, 2024
Published in: conference
ISSN: 2308-443X
ISBN: 978-1-68558-133-6
Location: Athens, Greece
Dates: from March 10, 2024 to March 14, 2024