Re:Anyone working on LLM tools for enhancing data quality?
by johannesboyne on Tuesday January 16, 2024 @03:49AM
(#39010997)
The combination is truly key, how we do it:
- Combining LLMs, gradient boosting, and multiple statistical/heuristic based approaches
- For LLMs: rely on (quite) large context length + fine-tuning
- The (ML) models are used to extract mathematically provable quality checks
- Combining LLMs, gradient boosting, and multiple statistical/heuristic based approaches - For LLMs: rely on (quite) large context length + fine-tuning - The (ML) models are used to extract mathematically provable quality checks