paper-with-me

홈 › Papers

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

2024-07-30 · Adam Wojciechowski, Mateusz Lango, Ondrej Dusek

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.

📄 PDF Abstract BibTeX arXiv:2407.20899

Code (1)

wojciechowskiofficial/flex 공식 구현 pytorch

Tasks

image-classificationImage ClassificationLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification

2026-03-19 · Isabel Rio-Torto, Jaime S. Cardoso, Luís F. Teixeira arxiv

Natural language explanations provide an inherently human-understandable way to explain black-box models, closely reflecting how radiologists convey their diagnoses in textual reports. Most works explicitly supervise the…

Explanation Generation

From Plausible to Actionable: A Position on LLM Self-Explanations

2026-07-17 · Elize Herrewijnen, Benedetta Muscato, Gizem Gezici, Fosca Giannotti arxiv

Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations. Such explanations have emerged as a promising directio…

Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models

2024-02-07 · Chirag Agarwal, Sree Harsha Tanneru, Himabindu Lakkaraju

Large Language Models (LLMs) are deployed as powerful tools for several natural language processing (NLP) applications. Recent works show that modern LLMs can generate self-explanations (SEs), which elicit their intermed…

Decision Making

Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models

2024-10-18 · Wei Jie Yeo, Ranjan Satapathy, Erik Cambria

Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. However, the faithfulness of these explanations should not be readily trusted at face value…

The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models

2024-04-04 · Noah Y. Siegel, Oana-Maria Camburu, Nicolas Heess, Maria Perez-Ortiz

In order to oversee advanced AI systems, it is important to understand their underlying decision-making process. When prompted, large language models (LLMs) can provide natural language explanations or reasoning traces t…

counterfactualDecision Making