Verif.ai: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917635858366464 |
|---|---|
| author | Košprdić, Miloš Ljajić, Adela Bašaragin, Bojana Medvecki, Darija Milošević, Nikola |
| author_facet | Košprdić, Miloš Ljajić, Adela Bašaragin, Bojana Medvecki, Darija Milošević, Nikola |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18589 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Verif.ai: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answers Košprdić, Miloš Ljajić, Adela Bašaragin, Bojana Medvecki, Darija Milošević, Nikola Information Retrieval Artificial Intelligence Computation and Language Machine Learning 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. |
| title | Verif.ai: Towards an Open-Source Scientific Generative Question-Answering System with Referenced and Verifiable Answers |
| topic | Information Retrieval Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2402.18589 |