llm-bradley-terry / docs /arena /disclaimer.md
jerome-white's picture
Allow Alpaca and Arena results to be presented in the same space
d4dddf1
|
raw
history blame contribute delete
No virus
802 Bytes

A newer version of the Gradio SDK is available: 4.39.0

Upgrade

Disclaimer

This Space is primarily intended for exploration. For now its results should be treated as points of reference rather than absolute facts. Viewers are encouraged to study the pipeline and understand the model to help put the results into context.

Suggestions for improving this Space from those familiar with Chatbot Arena or Bayesian data analysis are welcome! Please use the community to do so.

Resources

TODO

  • Extend the Stan model to incorporate ties and response presentation ordering

  • Add details of the MCMC chains

  • Automate data processing

  • Explicit documentation of the process