What Makes Two Language Models Think Alike?
This provides a method for researchers to analyze and compare neural representations across models and domains, though it is incremental in advancing interpretability tools.
The paper tackles the problem of understanding how architectural differences affect language model representations by proposing metric-learning encoding models (MLEMs) for feature-based comparison of layers across models like BERT, GPT-2, and Mamba, enabling transparent identification of linguistic features responsible for similarities and differences.
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.