Score: 0

Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

Published: April 14, 2025 | arXiv ID: 2504.09762v2

By: Subbarao Kambhampati , Kaya Stechly , Karthik Valmeekam and more

Potential Business Impact:

Makes computers "think" better, but it's tricky.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

Intermediate token generation (ITG), where a model produces output before the solution, has been proposed as a method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called "reasoning traces" or even "thoughts" -- implicitly anthropomorphizing the model, implying these tokens resemble steps a human might take when solving a challenging problem.In this paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research.

Page Count
12 pages

Category
Computer Science:
Artificial Intelligence