Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics Tasks

Aleksander Buszydlik, Karol Dobiczek, Michał Teodor Okoń, Konrad Skublicki, Philip Lippmann, Jie Yang


Anthology ID:
2023.artofsafety-1.1
Volume:
Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI
Month:
November
Year:
2023
Address:
Bali, Indonesia
Editor:
Alicia Parrish
Venues:
artofsafety | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–10
Language:
URL:
https://aclanthology.org/2023.artofsafety-1.1
DOI:
10.18653/v1/2023.artofsafety-1.1
Bibkey:
Cite (ACL):
Aleksander Buszydlik, Karol Dobiczek, Michał Teodor Okoń, Konrad Skublicki, Philip Lippmann, and Jie Yang. 2023. Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics Tasks. In Proceedings of the ART of Safety: Workshop on Adversarial testing and Red-Teaming for generative AI, pages 1–10, Bali, Indonesia. Association for Computational Linguistics.
Cite (Informal):
Red Teaming for Large Language Models At Scale: Tackling Hallucinations on Mathematics Tasks (Buszydlik et al., artofsafety-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.artofsafety-1.1.pdf