Bobae Jang

Key Skills

Software

Remotasks

Other

Scale AI

Top Subject Matter

AI chatbot response evaluation in Korean

AI voice response evaluation in Korean

AI image-generative response evaluation in Korean

Top Data Types

Audio

Image

Text

Top Task Types

Evaluation Rating

Prompt Response Writing SFT

Freelancer Overview

Before applying to OpenTrain AI, I worked with Outlier on projects that included, but were not limited to, AI response evaluation where I would score the AI response to a prompt using sets of criteria including instructions following, truthfulness, etc. I was able to keep a stream of jobs on the Outlier platform and built the foundation skillsets needed for AI data labeling tasks. Following guidelines for each task was the key to successfully evaluating AI responses.

Labeling Experience

AI Response Evaluation

Scale AITextEvaluation Rating

I evaluated AI responses in Korean using sets of criteria given by the client. On the projects, I evaluated the AI responses on the grounds of truthfulness, which checks the factuality of the information found in the response and instruction following, which pertains to whether the response addressed the prompt's explicit and implicit intentions. I mostly did evaluation tasks for different formats such as text, image, and voice responses.

I evaluated AI responses in Korean using sets of criteria given by the client. On the projects, I evaluated the AI responses on the grounds of truthfulness, which checks the factuality of the information found in the response and instruction following, which pertains to whether the response addressed the prompt's explicit and implicit intentions. I mostly did evaluation tasks for different formats such as text, image, and voice responses.

2024 - 2024

Education

Work History