Xue X.

Key Skills

Software

Other

Top Subject Matter

LLM fine-tuning with RLHF

Chinese language nuance

Generative AI storyboard creation for children’s picture stories

Top Data Types

Text

Image

Video

Document

Top Task Types

RLHF

Prompt + Response Writing (SFT)

Freelancer Overview

Part-time Project — Conducted RLHF for LLM fine-tuning (Datannotation.tech). Brings 8+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Datannotation.tech, Midjourney, and Nano Banana. Education includes Master of Arts, University of Dayton (2026) and Bachelor of Arts, Zhejiang University of Media and Communications (2013). AI-training focus includes data types such as Text and Image and labeling workflows including RLHF and Prompt + Response Writing (SFT).

Labeling Experience

Part-time Project — Generated storyboards with generative AI (Guangzhou Chuzhan Technology Co., Ltd)

ImagePrompt + Response Writing (SFT)

Produced children’s picture storyboards using generative AI tools to support consistent character design and visual storytelling. While not explicitly described as labeling, the work reflects AI training/data preparation practices around generating supervised visual story content. The output likely served as structured creative data for generative pipelines. • Used generative tools (e.g., Midjourney, Nano Banana) for storyboard creation. • Emphasized consistent character design across scenes. • Created visual narrative materials for children’s stories. • Coordinated prompts to produce coherent, story-aligned image drafts.

2026 - Present

Part-time Project — Conducted RLHF for LLM fine-tuning (Datannotation.tech)

TextRLHF

Conducted Reinforcement Learning from Human Feedback (RLHF) to fine-tune Large Language Models (LLMs) with emphasis on Simplified Chinese linguistic nuance. The work involved preparing and using human feedback signals to steer model outputs. This role aligns with AI training where labeled feedback guides optimization. • Focused on Simplified Chinese linguistic nuance in training objectives. • Utilized RLHF methodology for LLM fine-tuning. • Followed reinforcement learning with human preference/feedback loops. • Applied the training process to improve model behavior for Chinese language use.

2026 - Present

Education

Work History