EMNLP 2024system demonstrations6 citations

WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models

Prannaya Gupta, Le Qi Yau, Hao Han Low, I-Shiang Lee, Hugo Maximus Lim, Yu Xin Teoh, Koh Jia Hng, Dar Win Liew

Abstract

WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models (LLMs). It accommodates a diverse range of models, including both open-weight and API-based ones, and features over 35 safety benchmarks covering areas such as multilingual safety, exaggerated safety, and prompt injections. The framework supports both LLM and judge benchmarking, and incorporates custom mutators to test safety against various text-style mutations such as future tense and paraphrasing. Additionally, WalledEval introduces WalledGuard, a new, small and performant content moderation tool, and SGXSTest, a benchmark for assessing exaggerated safety in cultural contexts. We make WalledEval publicly available at https://github.com/walledai/walledeval with a demonstration video at https://youtu.be/50Zy97kj1MA.

BibTeX
@inproceedings{gupta-etal-2024-walledeval,
    title = "{W}alled{E}val: A Comprehensive Safety Evaluation Toolkit for Large Language Models",
    author = "Gupta, Prannaya  and
      Yau, Le Qi  and
      Low, Hao Han  and
      Lee, I-Shiang  and
      Lim, Hugo Maximus  and
      Teoh, Yu Xin  and
      Hng, Koh Jia  and
      Liew, Dar Win  and
      Bhardwaj, Rishabh  and
      Bhardwaj, Rajat  and
      Poria, Soujanya",
    editor = "Hernandez Farias, Delia Irazu  and
      Hope, Tom  and
      Li, Manling",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-demo.42/",
    doi = "10.18653/v1/2024.emnlp-demo.42",
    pages = "397--407"
}
WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models · EMNLP 2024