Fairly Evaluating Large Language Model-based Recommendation Needs Revisit the Cross-Entropy Loss.

Cong Xu Zhangchi Zhu Jun Wang Jianyong Wang Wei Zhang

Published in: CoRR (2024)

Keyphrases

cross entropy
log likelihood
maximum likelihood
natural language
recommender systems
evaluation metrics
collaborative filtering
error function
machine learning
language modeling
probabilistic context free grammars
neural network
feature selection
least squares
simulated annealing
ranking functions