XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Paul Röttger, Hannah Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, Dirk Hovy


Abstract
Without proper safeguards, large language models will readily follow malicious instructions and generate toxic content. This risk motivates safety efforts such as red-teaming and large-scale feedback learning, which aim to make models both helpful and harmless. However, there is a tension between these two objectives, since harmlessness requires models to refuse to comply with unsafe prompts, and thus not be helpful. Recent anecdotal evidence suggests that some models may have struck a poor balance, so that even clearly safe prompts are refused if they use similar language to unsafe prompts or mention sensitive topics. In this paper, we introduce a new test suite called XSTest to identify such eXaggerated Safety behaviours in a systematic way. XSTest comprises 250 safe prompts across ten prompt types that well-calibrated models should not refuse to comply with, and 200 unsafe prompts as contrasts that models, for most applications, should refuse. We describe XSTest’s creation and composition, and then use the test suite to highlight systematic failure modes in state-of-the-art language models as well as more general challenges in building safer language models.
Anthology ID:
2024.naacl-long.301
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5377–5400
Language:
URL:
https://aclanthology.org/2024.naacl-long.301
DOI:
Bibkey:
Cite (ACL):
Paul Röttger, Hannah Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, and Dirk Hovy. 2024. XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5377–5400, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models (Röttger et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.301.pdf
Copyright:
 2024.naacl-long.301.copyright.pdf