Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
By: Subbarao Kambhampati , Kaya Stechly , Karthik Valmeekam and more
Potential Business Impact:
Makes computers "think" better, but it's tricky.
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.
Similar Papers
Beyond Semantics: The Unreasonable Effectiveness of Reasonless Intermediate Tokens
Machine Learning (CS)
Teaches computers to think better, not just copy.
LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens
Computation and Language
Makes computer translators better by showing them how.
Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity
Artificial Intelligence
Models don't "think" more for harder problems.