most citedHow Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

1 citations · 1 across the 2 of their papers we have counts for

collaborators

2 papers

stat.ME2026

Variance Reduction Methods for Dirichlet Expectations

Ayeong Lee

Dirichlet distributions are probability measures on the unit simplex. They are often used as prior distributions in modeling categorical data, such as in topic analysis of text dat…

cs.CL2025★ 1 cited

How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Ayeong Lee, Ethan Che, Tianyi Peng

Chain-of-thought prompting has emerged as a powerful technique for enabling large language models (LLMs) to solve complex reasoning tasks. However, these reasoning chains can be ve…