Prompt Evaluator | AI Data Evaluator
I executed text classification and Named Entity Recognition (NER) tasks for various AI training datasets. Tasks involved prompt evaluation, response ranking, and bias or safety verification in AI-generated content. My contributions improved language model accuracy and safety across technical and regulatory vocabularies. • Text classification and NER labeling for LLM training datasets. • Evaluation and ranking of AI-generated responses for factuality. • Identification and reporting of bias or hallucinations in text outputs. • Support for model prompt engineering and optimization.