Abstract
Conversational AI systems can engage in unsafe behaviour when handling users’ medical queries that may have severe consequences and could even lead to deaths. Systems therefore need to be capable of both recognising the seriousness of medical inputs and producing responses with appropriate levels of risk. We create a corpus of human written English language medical queries and the responses of different types of systems. We label these with both crowdsourced and expert annotations. While individual crowdworkers may be unreliable at grading the seriousness of the prompts, their aggregated labels tend to agree with professional opinion to a greater extent on identifying the medical queries and recognising the risk types posed by the responses. Results of classification experiments suggest that, while these tasks can be automated, caution should be exercised, as errors can potentially be very serious.- Anthology ID:
- 2022.aacl-short.30
- Volume:
- Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- November
- Year:
- 2022
- Address:
- Online only
- Editors:
- Yulan He, Heng Ji, Sujian Li, Yang Liu, Chua-Hui Chang
- Venues:
- AACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 234–243
- Language:
- URL:
- https://aclanthology.org/2022.aacl-short.30
- DOI:
- Cite (ACL):
- Gavin Abercrombie and Verena Rieser. 2022. Risk-graded Safety for Handling Medical Queries in Conversational AI. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 234–243, Online only. Association for Computational Linguistics.
- Cite (Informal):
- Risk-graded Safety for Handling Medical Queries in Conversational AI (Abercrombie & Rieser, AACL-IJCNLP 2022)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2022.aacl-short.30.pdf