# Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency

Source: [Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency](<https://www.sota2.com/research/paper/68fa73941e209131cea5d5a7>)

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

Data updated: 2025-10-28T13:57:07.142Z

Authors: Maor Dikter, Tsachi Blau, Chaim Baskin

Published: 2024-06-13T06:04:34.000Z

## Abstract

Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as concepts, to inform their decision-making process and offer more accurate reasoning. As a result, the selection of concepts used in the model is of utmost significance. This study proposes \\underline{\\textbf{C}}onceptual \\underline{\\textbf{L}}earning via \\underline{\\textbf{E}}mbedding \\underline{\\textbf{A}}pproximations for \\underline{\\textbf{R}}einforcing Interpretability and Transparency, abbreviated as CLEAR, a framework for constructing a CBM for image classification. Using score matching and Langevin sampling, we approximate the embedding of concepts within the latent space of a vision-language model (VLM) by learning the scores associated with the joint distribution of images and concepts. A concept selection process is then employed to optimize the similarity between the learned embeddings and the predefined ones. The derived bottleneck offers insights into the CBM's decision-making process, enabling more comprehensive interpretations. Our approach was evaluated through extensive experiments and achieved state-of-the-art performance on various benchmarks. The code for our experiments is available at https://github.com/clearProject/CLEAR/tree/main

## 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/2406.08840>)

[PDF](<https://arxiv.org/pdf/2406.08840.pdf>)
