Response Evaluation
Conducted reinforcement to optimize large language model outputs. Evaluated responses based on instruction following, factuality and logic. My responsibilities included identifying hallucinations, and ranking conversations.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
In my previous role as a Generalist for Outlier AI, I specialized in refining and evaluating LLM outputs. I usually received projects centered on conversations that involved fact-checking, safety auditing and ranking based on adherence to instructions. Examples of tasks include comparison & ranking, justification writing, fact checking, search query generation and data labelling. I consistently had great reviews because of my attention to detail derived from years of experience in Underwriting and Finance. In addition, I have an MBA from a top school and a strong background in Industrial Design. This combination empowers me to handle the rigors of data labelling. I excel at spotting discrepancies in data and streamlining workflows. My experience managing high value data in the public sector and real estate finance has given me a solid foundation for this role.
Conducted reinforcement to optimize large language model outputs. Evaluated responses based on instruction following, factuality and logic. My responsibilities included identifying hallucinations, and ranking conversations.
Bachelor of Science, Industrial Design
Master of Business Administration, Business Administration
Assistant Right of Way Agent
Administrative Support Specialist