黄权

Key Skills

Software

Other

Clickworker

Top Subject Matter

Large language model (LLM) evaluation and RLHF feedback for math/physics and general reasoning

Top Data Types

Text

Image

Video

Top Task Types

RLHF

Prompt + Response Writing (SFT)

Evaluation/Rating

Freelancer Overview

Experienced in using mainstream AI tools for prompt engineering, response evaluation, structured reasoning, and AI-assisted workflows. Background includes technical sales engineering and STEM education, with strong analytical thinking and detail-oriented communication skills. Interested in LLM evaluation, RLHF tasks, Chinese language annotation, and reasoning-focused AI training projects.

Labeling Experience

AI Training & LLM Evaluation & RLHF / Prompt Engineering (Independent AI Workflow Practice)

OtherTextRLHF

Provided hands-on LLM evaluation with an emphasis on RLHF-style quality checks and iterative prompt improvements. Focused on identifying output issues including hallucinations, logical inconsistencies, factual inaccuracies, and formatting problems. Used structured evaluation guidelines to score and validate responses against expected behavior. • Performed response quality evaluation aligned to instruction-following requirements • Checked factuality and internal logic for mathematical/physics reasoning tasks • Validated formatting and adherence to specified output structures • Repeated quality-focused review cycles to ensure consistency

Present

Education

Work History