Side By Side Response Evaluation
Evaluate 2 LLM responses to the same prompt and rate them individually. Then rate and select which was the better response, and write a justification for my choice.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
I have worked on many projects in AI training, including both completing tasks and reviewing others' work for quality being submitted to clients. My experience includes both basic LLM response rating as well as more complex prompt writing, rubric design, and response writing. I've contributed to tasks in voice and music recognition, as well as text and image evaluation and classification.
Evaluate 2 LLM responses to the same prompt and rate them individually. Then rate and select which was the better response, and write a justification for my choice.
Large project creating full data sets for LLMs. Created up to 3 prompts, a core model prompt, categorization prompt as well as user prompt. The prompts had to be complex to cause 2 models to fail. Would then write a rubric based on the 3 prompts. I would then evaluate the 2 models based on the rubric I created to give them scores and select which one did better. I would then write the perfect response based on the rubric.
Recorded audio prompts for specified categories. The LLM would transcribe what was heard and I would correct the transcription as needed.
I was a reviewer/QA on this project. The AI gave suggestions of what instruments and voices were heard, and an agent then corrected it and transcribed it accurately. I verified the information and corrected the work again.
High School Diploma, Highschool
Independent Contractor
Customer Care Representative (Technical Support)