A Multimodal Automated Interpretability Agent

TL;DR

MAIA is a multimodal system that automates neural network interpretability tasks using tools for input synthesis, exemplar retrieval, and result summarization, aiding in understanding and debugging vision models.

Contribution

It introduces MAIA, a novel multimodal interpretability agent that automates complex interpretability tasks for neural networks, integrating multiple tools for comprehensive analysis.

Findings

MAIA produces feature descriptions comparable to human experts.

It helps reduce sensitivity to spurious features in models.

MAIA can identify inputs likely to be misclassified.

Abstract

This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained vision-language model with a set of tools that support iterative experimentation on subcomponents of other models to explain their behavior. These include tools commonly used by human interpretability researchers: for synthesizing and editing inputs, computing maximally activating exemplars from real-world datasets, and summarizing and describing experimental results. Interpretability experiments proposed by MAIA compose these tools to describe and explain system behavior. We evaluate applications of MAIA to computer vision models. We first characterize MAIA's ability to describe (neuron-level) features in learned representations of images. Across several trained models and a novel dataset of synthetic vision neurons with paired ground-truth descriptions, MAIA produces descriptions comparable to those generated by expert human experimenters. We then show that MAIA can aid in two additional interpretability tasks: reducing sensitivity to spurious features, and automatically identifying inputs likely to be mis-classified.