Why do explanations fail? A typology and discussion on failures in XAI

• URL: http://arxiv.org/abs/2405.13474v2
• Date: Thu, 16 Oct 2025 08:03:54 GMT
• Title: Why do explanations fail? A typology and discussion on failures in XAI
• Authors: Clara Bove, Thibault Laugel, Marie-Jeanne Lesot, Charles Tijus, Marcin Detyniecki,
• Abstract summary: We argue that the resulting harms arise from a complex overlap of multiple failures in XAI.<n>We propose a typological framework that helps revealing the nuanced complexities of explanation failures.
• Score: 5.366368559381279
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Machine Learning models achieve unprecedented levels of performance, the XAI domain aims at making these models understandable by presenting end-users with intelligible explanations. Yet, some existing XAI approaches fail to meet expectations: several issues have been reported in the literature, generally pointing out either technical limitations or misinterpretations by users. In this paper, we argue that the resulting harms arise from a complex overlap of multiple failures in XAI, which existing ad-hoc studies fail to capture. This work therefore advocates for a holistic perspective, presenting a systematic investigation of limitations of current XAI methods and their impact on the interpretation of explanations. % By distinguishing between system-specific and user-specific failures, we propose a typological framework that helps revealing the nuanced complexities of explanation failures. Leveraging this typology, we discuss some research directions to help practitioners better understand the limitations of XAI systems and enhance the quality of ML explanations.

Related papers

• Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions [95.59915390053588]
  This study focuses on Explainable Artificial Intelligence (XAI) approaches-focusing on deep neural networks (DNNs) and large language models (LLMs)<n>We discuss critical symptoms that stem from deeper root causes (i.e., two paradoxes, two conceptual confusions, and five false assumptions)<n>To move beyond XAI's limitations, we propose a four-pronged paradigm shift toward reliable and certified AI development.
  arXiv  Detail & Related papers  (2026-02-27T16:58:27Z)
• Emergent, not Immanent: A Baradian Reading of Explainable AI [37.51348424835944]
  We argue that interpretations emerge from situated entanglements of the AI model with humans, context, and the interpretative apparatus.<n>We propose design directions for XAI interfaces that support emergent interpretation.
  arXiv  Detail & Related papers  (2026-01-21T14:32:40Z)
• On the Hardness of Computing Counterfactual and Semifactual Explanations in XAI [5.172213041663734]
  We show that in many cases, generating explanations is computationally hard.<n>We discuss the implications for the XAI community and for policymakers seeking to regulate explanations in AI.
  arXiv  Detail & Related papers  (2026-01-14T13:02:24Z)
• Onto-Epistemological Analysis of AI Explanations [8.570570532582446]
  We discuss explainable AI (XAI) methods that provide explanations of the models' decision process.<n>We show how seemingly small technical changes to an XAI method may correspond to important differences in the underlying assumptions about explanations.<n>We also highlight the risks of ignoring the underlying onto-epistemological paradigm when choosing an XAI method for a given application.
  arXiv  Detail & Related papers  (2025-10-03T13:36:57Z)
• Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanations [1.6855625805565164]
  Large Language Models (LLMs) are used to translate outputs from explainability techniques, like feature-attribution weights, into a natural language explanation. Recent findings suggest translating into human-like explanations does not necessarily enhance user understanding and may instead lead to overreliance on AI systems.
  arXiv  Detail & Related papers  (2025-04-16T18:45:18Z)
• Explainable artificial intelligence (XAI): from inherent explainability to large language models [0.0]
  Explainable AI (XAI) techniques facilitate the explainability or interpretability of machine learning models. This paper details the advancements of explainable AI methods, from inherently interpretable models to modern approaches. We review explainable AI techniques that leverage vision-language model (VLM) frameworks to automate or improve the explainability of other machine learning models.
  arXiv  Detail & Related papers  (2025-01-17T06:16:57Z)
• More Questions than Answers? Lessons from Integrating Explainable AI into a Cyber-AI Tool [1.5711133309434766]
  We describe a preliminary case study on the use of XAI for source code classification. We find that the outputs of state-of-the-art saliency explanation techniques are lost in translation when interpreted by people with little AI expertise. We outline unaddressed gaps in practical and effective XAI, then touch on how emerging technologies like Large Language Models (LLMs) could mitigate these existing obstacles.
  arXiv  Detail & Related papers  (2024-08-08T20:09:31Z)
• Is Task-Agnostic Explainable AI a Myth? [0.0]
  Our work serves as a framework for unifying the challenges of contemporary explainable AI (XAI) We demonstrate that while XAI methods provide supplementary and potentially useful output for machine learning models, researchers and decision-makers should be mindful of their conceptual and technical limitations. We examine three XAI research avenues spanning image, textual, and graph data, covering saliency, attention, and graph-type explainers.
  arXiv  Detail & Related papers  (2023-07-13T07:48:04Z)
• XAI-TRIS: Non-linear image benchmarks to quantify false positive post-hoc attribution of feature importance [1.3958169829527285]
  A lack of formal underpinning leaves it unclear as to what conclusions can safely be drawn from the results of a given XAI method. This means that challenging non-linear problems, typically solved by deep neural networks, presently lack appropriate remedies. We show that popular XAI methods are often unable to significantly outperform random performance baselines and edge detection methods.
  arXiv  Detail & Related papers  (2023-06-22T11:31:11Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• Impact Of Explainable AI On Cognitive Load: Insights From An Empirical Study [0.0]
  This study measures cognitive load, task performance, and task time for implementation-independent XAI explanation types using a COVID-19 use case. We found that these explanation types strongly influence end-users' cognitive load, task performance, and task time.
  arXiv  Detail & Related papers  (2023-04-18T09:52:09Z)
• Towards Human Cognition Level-based Experiment Design for Counterfactual Explanations (XAI) [68.8204255655161]
  The emphasis of XAI research appears to have turned to a more pragmatic explanation approach for better understanding. An extensive area where cognitive science research may substantially influence XAI advancements is evaluating user knowledge and feedback. We propose a framework to experiment with generating and evaluating the explanations on the grounds of different cognitive levels of understanding.
  arXiv  Detail & Related papers  (2022-10-31T19:20:22Z)
• Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI [65.44737844681256]
  A lack of consensus on how to evaluate explainable AI (XAI) hinders the advancement of the field. We argue that one way to close the gap is to develop evaluation methods that account for different user requirements.
  arXiv  Detail & Related papers  (2022-06-22T05:17:33Z)
• Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement [75.00655434905417]
  Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex machine learning (ML) models. This paper offers a comprehensive overview over techniques that apply XAI practically for improving various properties of ML models. We show empirically through experiments on toy and realistic settings how explanations can help improve properties such as model generalization ability or reasoning.
  arXiv  Detail & Related papers  (2022-03-15T15:44:28Z)
• CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Models [84.32751938563426]
  We propose a new explainable AI (XAI) framework for explaining decisions made by a deep convolutional neural network (CNN) In contrast to the current methods in XAI that generate explanations as a single shot response, we pose explanation as an iterative communication process. Our framework generates sequence of explanations in a dialog by mediating the differences between the minds of machine and human user.
  arXiv  Detail & Related papers  (2021-09-03T09:46:20Z)
• Explanatory Pluralism in Explainable AI [0.0]
  I chart a taxonomy of types of explanation and the associated XAI methods that can address them. When we look to expose the inner mechanisms of AI models, we produce Diagnostic-explanations. When we wish to form stable generalizations of our models, we produce Expectation-explanations. Finally, when we want to justify the usage of a model, we produce Role-explanations.
  arXiv  Detail & Related papers  (2021-06-26T09:02:06Z)
• Explainability in Deep Reinforcement Learning [68.8204255655161]
  We review recent works in the direction to attain Explainable Reinforcement Learning (XRL) In critical situations where it is essential to justify and explain the agent's behaviour, better explainability and interpretability of RL models could help gain scientific insight on the inner workings of what is still considered a black box.
  arXiv  Detail & Related papers  (2020-08-15T10:11:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.