IS TRANSFORMER A STOCHASTIC PARROT? A CASE STUDY IN SIMPLE ARITHMETIC TASK
Keywords: large language model, interpretability
Abstract: Large pre-trained language models have demonstrated impressive capabilities, but
there is still much to learn about how they operate. In this study, we
conduct a investigation of the autoregressive transformer’s ability to
perform basic addition operations.
Specifically, by using causal analysis we found that a few different attention heads in the middle layers control the addition carry, with each head processing carries of different lengths. Due to the lack of globality in these attention heads, the model struggles to handle long-sequence addition tasks. By performing inference intervention on mistral-7B, partial task performance can be restored, with the accuracy on 20-digit long-sequence additions from 2\% to 38\%. Through
fine-tuning, a new mechanism branches out for handling more complex cases, yet
it still faces challenges with length generalization. Our research reveals how the
model performs addition, and further provides insights into the debate on whether
these models are merely statistical.
Primary Area: interpretability and explainable AI
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 10945
Loading