Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models
Elena Stringli, Maria Lymperaiou, Giorgos Filandrianos, Athanasios Voulodimos, Giorgos Stamou
2/18/2025
cs.CL
No confident code implementation found for this paper. 2 possible matches can be shown below.
Abstract
Inverse tasks can uncover potential reasoning gaps as Large Language Models (LLMs) scale up. In this work, we explore the redefinition task, in which we assign alternative values to well-known physical constants and units of measure, prompting LLMs to respond accordingly. Our findings show that not only does model performance degrade with scale, but its false confidence also rises. Moreover, while factors such as prompting strategies or response formatting are influential, they do not preclude LLMs from anchoring to memorized values.
