RLHF
TextRLHF
Spearheaded a complex NLP project evaluating and ranking large language model (LLM) responses for factual accuracy, safety, and tone.
Authored highly detailed justification summaries to successfully guide Reinforcement Learning from Human Feedback (RLHF).
Consistently maintained quality assurance score across complex prompts involving reasoning, coding, and creative writing.
Spearheaded a complex NLP project evaluating and ranking large language model (LLM) responses for factual accuracy, safety, and tone. Authored highly detailed justification summaries to successfully guide Reinforcement Learning from Human Feedback (RLHF). Consistently maintained quality assurance score across complex prompts involving reasoning, coding, and creative writing.
2023 - 2023