# Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP

Source: [Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP](<https://www.sota2.com/research/paper/68fa70761e209131cea4b3ab>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:42:00.795Z

Authors: Vedant Palit, Rohan Pandey, Aryaman Arora, Paul Pu Liang

Published: 2023-08-27T18:46:47.000Z

## Abstract

Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy spans of text, capture factual knowledge, and more, they remain unusable for multimodal models since adapting these tools to the vision-language domain requires considerable architectural changes. In this work, we adapt a unimodal causal tracing tool to BLIP to enable the study of the neural mechanisms underlying image-conditioned text generation. We demonstrate our approach on a visual question answering dataset, highlighting the causal relevance of later layer representations for all tokens. Furthermore, we release our BLIP causal tracing tool as open source to enable further experimentation in vision-language mechanistic interpretability by the community. Our code is available at https://github.com/vedantpalit/Towards-Vision-Language-Mechanistic-Interpretability.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.14179>)

[PDF](<https://arxiv.org/pdf/2308.14179.pdf>)
