Gabriel Chua
@gabrielchua.bsky.social
Machine Learning at GovTech
gabrielchua.me
gabrielchua.me
🚨 new applied ai paper from govtech
LLMs are powerful, but they're prone to off-topic misuse, where users push them beyond their intended scope. Think harmful prompts, jailbreaks, and misuse. So how do we build better guardrails?
arxiv.org/abs/2411.12946
LLMs are powerful, but they're prone to off-topic misuse, where users push them beyond their intended scope. Think harmful prompts, jailbreaks, and misuse. So how do we build better guardrails?
arxiv.org/abs/2411.12946
November 27, 2024 at 12:57 AM
🚨 new applied ai paper from govtech
LLMs are powerful, but they're prone to off-topic misuse, where users push them beyond their intended scope. Think harmful prompts, jailbreaks, and misuse. So how do we build better guardrails?
arxiv.org/abs/2411.12946
LLMs are powerful, but they're prone to off-topic misuse, where users push them beyond their intended scope. Think harmful prompts, jailbreaks, and misuse. So how do we build better guardrails?
arxiv.org/abs/2411.12946