What Makes Two Language Models Think Alike?
Abstract: Do architectural differences significantly affect the way models represent and process language? We propose a new approach, based on metric-learning encoding models (MLEMs), as a first step to answer this question. The approach provides a feature-based comparison of how any two layers of any two models represent linguistic information. We apply the method to BERT, GPT-2 and Mamba. Unlike previous methods, MLEMs offer a transparent comparison, by identifying the specific linguistic features responsible for similarities and differences. More generally, the method uses formal, symbolic descriptions of a domain, and use these to compare neural representations. As such, the approach can straightforwardly be extended to other domains, such as speech and vision, and to other neural systems, including human brains.
Paper Type: Short
Research Area: Interpretability and Analysis of Models for NLP
Research Area Keywords: analysis, feature attribution, phrase/sentence embedding
Contribution Types: Model analysis & interpretability
Languages Studied: English
Submission Number: 4627
Loading