A newer version of the Gradio SDK is available:
5.41.1
metadata
title: RLHF Pairwise Annotation Demo
emoji: 🎯
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit
datasets:
- openbmb/UltraFeedback
🎯 AI Alignment: Binary Preference Annotation
This app simulates the data annotation process used in RLHF (Reinforcement Learning from Human Feedback) training. Users compare two AI completions and select which one is better.
How it works
- The app loads random examples from the UltraFeedback dataset
- Users see a prompt and two AI completions
- Users select which completion is better or skip if unsure
- All annotations are saved to a public dataset for research purposes