#artificial intelligence
Dec 2025
Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought Length
LaRT is proposed, which jointly models both the response accuracy and CoT length by introducing a key correlation parameter between the latent ability and the latent speed, and derives an efficient stochastic approximation Expectation-Maximization algorithm for parameter estimation.
Zhi-Yu Xu, Jia Liu, Yixin Wang et al.
· arXiv.org · 7 citations
· ⚡2