all AI news
Predictive Human Preference: From Model Ranking to Model Routing
Chip Huyen huyenchip.com
Table of contents
Ranking Models Using Human Preference
…. How Preferential Ranking Works
…. Correctness of Chatbot Arena Ranking
…….. Eval data
…….. Results
Predicting Human Preference For Each Prompt
…. Experiment setup
…. Experiment results
…….. Domain-specific and query-specific leaderboards
Conclusion
Human preference has emerged to be both the Northstar and a powerful tool for AI model development. Human preference guides post-training techniques including RLHF and DPO. Human preference is also used to rank AI models, as used …
arena chatbot contents data domain experiment human predictive prompt query ranking results routing setup table