Circuit Breakers for AI: Interrupting Harmful Outputs Through Representation Engineering
Marktechpost
SEPTEMBER 28, 2024
Robustness evaluation employs safety prompts and categorizes results based on MM-SafetyBench scenarios. We are inviting startups, companies, and research institutions who are working on small language models to participate in this upcoming ‘Small Language Models’ Magazine/Report by Marketchpost.com. Click here to set up a call!
Let's personalize your content