Position Paper Argues Against Calling LLM Intermediate Tokens 'Reasoning'
A position paper by Subbarao Kambhampati and colleagues, revised on arXiv (2504.09762, v4), argues that intermediate token generation in language models should not be anthropomorphized as 'reasoning' or 'thinking' traces. The authors contend that such terminology implicitly implies human-like cognitive steps, which may mislead interpretation of model behavior.
Coverage timeline
Hacker Newsnunodonato
# Computer Science > Artificial Intelligence **arXiv:2504.09762** (cs) Submitted on 14 Apr 2025 ([v1), last revised 9 Jun 2026 (this version, v4)] # Title:Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces! Authors:Subbarao Kambhampati, Karthik Valmeekam, Siddhant Bhambri, Vardhan Palod, Lucas Saldyt, Kaya Stechly, Soumya Rani Samineni, Durgesh Kalwar, Upasana Biswas View a PDF of the paper titled Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!, by Subbarao Kambhampati and 8 other authors View PDFHTML (experimental) > Abstract:Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solvi