Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models

ACL ARR 2025 February Submission4315 Authors

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.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: prompting, scaling, hardness of samples, reasoning, interpretability

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 4315