On the Chatbot Arena and SLAM datasets, Elo is hyperparameter-sensitive and order-unstable, while Bradley-Terry preserves transitivity best and Glicko offers the most stable accuracy.
The Bowl Championship Series: A Mathematical Review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We discuss individual components of the college football Bowl Championship Series, compare with a simple algorithm defined by random walks on a biased graph, attempt to predict whether the proposed changes will truly lead to increased BCS bowl access for non-BCS schools, and conclude by arguing that the true problem with the BCS Standings lies not in the computer algorithms, but rather in misguided addition.
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI Combat
On the Chatbot Arena and SLAM datasets, Elo is hyperparameter-sensitive and order-unstable, while Bradley-Terry preserves transitivity best and Glicko offers the most stable accuracy.