AAAI 2024technical11 citations
LLMGuard: Guarding against Unsafe LLM Behavior
Shubh Goyal, Medha Hira, Shubham Mishra, Sukriti Goyal, Arnav Goel, Niharika Dadu, Kirushikesh DB, Sameep Mehta
Abstract
Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns. To alleviate this, we present "LLMGuard", a tool that monitors user interactions with an LLM application and flags content against specific behaviours or conversation topics. To do this robustly, LLMGuard employs an ensemble of detectors.
BibTeX
@article{Goyal_Hira_Mishra_Goyal_Goel_Dadu_DB_Mehta_Madaan_2024, title={LLMGuard: Guarding against Unsafe LLM Behavior}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30566}, DOI={10.1609/aaai.v38i21.30566}, abstractNote={Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns.
To alleviate this, we present "LLMGuard", a tool that monitors user interactions with an LLM application and flags content against specific behaviours or conversation topics. To do this robustly, LLMGuard employs an ensemble of detectors.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Goyal, Shubh and Hira, Medha and Mishra, Shubham and Goyal, Sukriti and Goel, Arnav and Dadu, Niharika and DB, Kirushikesh and Mehta, Sameep and Madaan, Nishtha}, year={2024}, month={Mar.}, pages={23790-23792} }