LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multimodal Large Language Models
This work addresses the problem of interpretability in deep generative models for researchers and practitioners, though it appears incremental as it builds on existing explainable AI and multimodal methods.
The paper tackled the challenge of explaining latent variables in deep generative models by introducing LatentExplainer, a framework that uses multimodal large language models to generate semantically meaningful explanations, resulting in superior performance in generating high-quality explanations as demonstrated on real-world and synthetic datasets.
Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in interpreting machine learning models, understanding latent variables in generative models remains challenging. This paper introduces LatentExplainer, a framework for automatically generating semantically meaningful explanations of latent variables in deep generative models. LatentExplainer tackles three main challenges: inferring the meaning of latent variables, aligning explanations with inductive biases, and handling varying degrees of explainability. Our approach perturbs latent variables, interprets changes in generated data, and uses multimodal large language models (MLLMs) to produce human-understandable explanations. We evaluate our proposed method on several real-world and synthetic datasets, and the results demonstrate superior performance in generating high-quality explanations for latent variables. The results highlight the effectiveness of incorporating inductive biases and uncertainty quantification, significantly enhancing model interpretability.