# Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach

Source: [Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach](<https://www.sota2.com/research/paper/68fa77771e209131cea734e1>)

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

Data updated: 2025-10-27T06:49:55.154Z

Authors: Adam Wojciechowski, Mateusz Lango, Ondrej Dusek

Published: 2024-07-30T15:17:15.000Z

## Abstract

Existing explanation methods for image classification struggle to provide faithful and plausible explanations. This paper addresses this issue by proposing a post-hoc natural language explanation method that can be applied to any CNN-based classifier without altering its training process or affecting predictive performance. By analysing influential neurons and the corresponding activation maps, the method generates a faithful description of the classifier's decision process in the form of a structured meaning representation, which is then converted into text by a language model. Through this pipeline approach, the generated explanations are grounded in the neural network architecture, providing accurate insight into the classification process while remaining accessible to non-experts. Experimental results show that the NLEs constructed by our method are significantly more plausible and faithful. In particular, user interventions in the neural network structure (masking of neurons) are three times more effective than the baselines.

## 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/2407.20899>)

[PDF](<https://arxiv.org/pdf/2407.20899.pdf>)