My experience
LLM evaluation and correction
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
A Half year experience in data labeling and AI training in other platforms especially in Japanese. I was involved in LLM model evaluation and correction. Outlier January 2025~September 2025 The primary goal of the task is to create challenging, real-life, and localized prompts that cause deviation (failure) across the models, and then build a precise rubric to evaluate the quality of their responses. The use of ChatGPT or any other AI tool is strictly prohibited for writing prompts, reference texts, criteria, justifications, or evaluating responses. The core objective of the task is to ensure that each translated prompt and response sounds natural and fluent in the target language. Your focus must be solely on the naturalness of the translation; you cannot alter the original prompt's core request or the model's response strategy Revise AI transcribed sentences about daily life conversation by Japanese speakers.
LLM evaluation and correction
Bachelor of Science, Materials Science and Engineering
Project Engineer
PCB Development Engineer