AI Trainer (RLHF / SFT)
Scale AITextRLHFPrompt Response Writing SFT
Classifying, scoring, and fine-tuning responses from generative AI models (LLMs) to match human preferences in a collaborative and safe manner using specific cultural lenses.
Classifying, scoring, and fine-tuning responses from generative AI models (LLMs) to match human preferences in a collaborative and safe manner using specific cultural lenses.
2024