Explainable AI needs formal notions of explanation correctness

• URL: http://arxiv.org/abs/2409.14590v2
• Date: Thu, 26 Sep 2024 12:29:45 GMT
• Title: Explainable AI needs formal notions of explanation correctness
• Authors: Stefan Haufe, Rick Wilming, Benedict Clark, Rustam Zhumagambetov, Danny Panknin, Ahcène Boubekki,
• Abstract summary: Machine learning in critical domains such as medicine poses risks and requires regulation. One requirement is that decisions of ML systems in high-risk applications should be human-understandable. In its current form, XAI is unfit to provide quality control for ML; it itself needs scrutiny.
• Score: 2.1309989863595677
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The use of machine learning (ML) in critical domains such as medicine poses risks and requires regulation. One requirement is that decisions of ML systems in high-risk applications should be human-understandable. The field of "explainable artificial intelligence" (XAI) seemingly addresses this need. However, in its current form, XAI is unfit to provide quality control for ML; it itself needs scrutiny. Popular XAI methods cannot reliably answer important questions about ML models, their training data, or a given test input. We recapitulate results demonstrating that popular XAI methods systematically attribute importance to input features that are independent of the prediction target. This limits their utility for purposes such as model and data (in)validation, model improvement, and scientific discovery. We argue that the fundamental reason for this limitation is that current XAI methods do not address well-defined problems and are not evaluated against objective criteria of explanation correctness. Researchers should formally define the problems they intend to solve first and then design methods accordingly. This will lead to notions of explanation correctness that can be theoretically verified and objective metrics of explanation performance that can be assessed using ground-truth data.

Related papers

• CHILLI: A data context-aware perturbation method for XAI [3.587367153279351]
  The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. We propose a novel framework, CHILLI, for incorporating data context into XAI by generating contextually aware perturbations. This is shown to improve both the soundness and accuracy of the explanations.
  arXiv  Detail & Related papers  (2024-07-10T10:18:07Z)
• The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
  Large Language Models (LLMs) are foundational to AI advancements. LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
  arXiv  Detail & Related papers  (2024-03-23T09:26:15Z)
• R-Tuning: Instructing Large Language Models to Say `I Don't Know' [66.11375475253007]
  Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. Previous instruction tuning methods force the model to complete a sentence no matter whether the model knows the knowledge or not. We present a new approach called Refusal-Aware Instruction Tuning (R-Tuning) Experimental results demonstrate R-Tuning effectively improves a model's ability to answer known questions and refrain from answering unknown questions.
  arXiv  Detail & Related papers  (2023-11-16T08:45:44Z)
• A Survey of Machine Unlearning [56.017968863854186]
  Recent regulations now require that, on request, private information about a user must be removed from computer systems. ML models often remember' the old data. Recent works on machine unlearning have not been able to completely solve the problem.
  arXiv  Detail & Related papers  (2022-09-06T08:51:53Z)
• BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence [1.2948254191169823]
  We show how varying perturbations can help to avoid potentially flawed conclusions. We also show how treatment of categorical variables is an important consideration in both post-hoc explainability and ablation studies.
  arXiv  Detail & Related papers  (2022-07-12T14:38:37Z)
• Explaining Any ML Model? -- On Goals and Capabilities of XAI [2.236663830879273]
  We argue that the goals and capabilities of XAI algorithms are far from being well understood. We show that users can ask diverse questions, but that only one of them can be answered by current XAI algorithms.
  arXiv  Detail & Related papers  (2022-06-28T11:09:33Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)
• A Comparative Approach to Explainable Artificial Intelligence Methods in Application to High-Dimensional Electronic Health Records: Examining the Usability of XAI [0.0]
  XAI aims to produce a demonstrative factor of trust, which for human subjects is achieved through communicative means. The ideology behind trusting a machine to tend towards the livelihood of a human poses an ethical conundrum. XAI methods produce visualization of the feature contribution towards a given models output on both a local and global level.
  arXiv  Detail & Related papers  (2021-03-08T18:15:52Z)
• Data Representing Ground-Truth Explanations to Evaluate XAI Methods [0.0]
  Explainable artificial intelligence (XAI) methods are currently evaluated with approaches mostly originated in interpretable machine learning (IML) research. We propose to represent explanations with canonical equations that can be used to evaluate the accuracy of XAI methods.
  arXiv  Detail & Related papers  (2020-11-18T16:54:53Z)
• 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)
• An Information-Theoretic Approach to Personalized Explainable Machine Learning [92.53970625312665]
  We propose a simple probabilistic model for the predictions and user knowledge. We quantify the effect of an explanation by the conditional mutual information between the explanation and prediction.
  arXiv  Detail & Related papers  (2020-03-01T13:06:29Z)

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.