paper-with-me

Papers

Evaluating Model Explanations without Ground Truth

2025-05-15 · Kaivalya Rawal, Zihao Fu, Eoin Delaney, Chris Russell

There can be many competing and contradictory explanations for a single model prediction, making it difficult to select which one to use. Current explanation evaluation frameworks measure quality by comparing against ideal "ground-truth" explanations, or by verifying model sensitivity to important inputs. We outline the limitations of these approaches, and propose three desirable principles to ground the future development of explanation evaluation strategies for local feature importance explanations. We propose a ground-truth Agnostic eXplanation Evaluation framework (AXE) for evaluating and comparing model explanations that satisfies these principles. Unlike prior approaches, AXE does not require access to ideal ground-truth explanations for comparison, or rely on model sensitivity - providing an independent measure of explanation quality. We verify AXE by comparing with baselines, and show how it can be used to detect explanation fairwashing. Our code is available at https://github.com/KaiRawal/Evaluating-Model-Explanations-without-Ground-Truth.

📄 PDF Abstract BibTeX arXiv:2505.10399

Code (1)

kairawal/evaluating-model-explanations-without-ground-truth 공식 구현 pytorch

Tasks

Feature ImportancemodelSensitivity

Similar Papers 제목 키워드 기반

The Blame Problem in Evaluating Local Explanations, and How to Tackle it

2023-10-05 · Amir Hossein Akhavan Rahnama

The number of local model-agnostic explanation techniques proposed has grown rapidly recently. One main reason is that the bar for developing new explainability techniques is low due to the lack of optimal evaluation mea…

Evaluating the Ability of Explanations to Disambiguate Models in a Rashomon Set

2026-01-13 · Kaivalya Rawal, Eoin Delaney, Zihao Fu, Sandra Wachter 외 arxiv

Explainable artificial intelligence (XAI) is concerned with producing explanations indicating the inner workings of models. For a Rashomon set of similarly performing models, explanations provide a way of disambiguating …

Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning

2022-02-17 · Juntao Tan, Shijie Geng, Zuohui Fu, Yingqiang Ge 외

Structural data well exists in Web applications, such as social networks in social media, citation networks in academic websites, and threads data in online forums. Due to the complex topology, it is difficult to process…

Causal InferencecounterfactualGraph Neural Network

Evaluating Explainability for Graph Neural Networks

2022-08-19 · Chirag Agarwal, Owen Queen, Himabindu Lakkaraju, Marinka Zitnik

As post hoc explanations are increasingly used to understand the behavior of graph neural networks (GNNs), it becomes crucial to evaluate the quality and reliability of GNN explanations. However, assessing the quality of…

Evaluating Local Model-Agnostic Explanations of Learning to Rank Models with Decision Paths

2022-03-04 · Amir Hossein Akhavan Rahnama, Judith Butepage

Local explanations of learning-to-rank (LTR) models are thought to extract the most important features that contribute to the ranking predicted by the LTR model for a single data point. Evaluating the accuracy of such ex…

Feature ImportanceLearning-To-Rank