This work proposes''Rule of Thumb''(RoT) explanations, a new approach to XAI based upon a novel formulation that identifies the most relevant features for predicting the behaviour of an AI system, for a particular datapoint.
Abstract
Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose''Rule of Thumb''(RoT) explanations, a new approach to XAI based upon a novel formulation that identifies the most relevant features for predicting the behaviour of an AI system, for a particular datapoint. We show how RoT is well-suited to enable XAI in: (a) zero-shot classification using large language models (LLMs), (b) auditing of opaque AI systems without model access, and (c) the use of AI in scientific discovery. Additionally, RoT meets specific requirements from leading AI regulations, provides a familiar interface and visualisations for XAI practitioners, is model-agnostic, and is substantially faster than alternatives. Code available at: https://github.com/KaiRawal/Rule-of-Thumb-Explaining-Artificial-Intelligence-Systems-using-Partial-Information
The study suggests that explainable AI is a crucial factor in building intelligent, reliable, accountable, transparent, and effective AI-powered systems that can be deployed in realistic environments for decision making.
Kirankumar Pundlik Mohurle, S. Sahare, Yugant Rupesh Dhoke et al.· International Journal of Eng...· 0 citations
Experimental findings show the effectiveness of XAI techniques to enhance interpretability without causing a major loss in predictive accuracy and the practical implications, limitations, and research directions on the future of explainable and trustworthy AI systems.
Unknown authors· International Journal of App...· 0 citations
A methodology is advanced to embed explainability in the AI decision-making process, starting from data preprocessing to generating explanations and human evaluation, and the results highlight the potential of explainability to enhance human comprehension and foster responsible use of AI systems in high-stakes decision...
Mahabala H. N.· International Journal of Mod...· 0 citations
A thorough and stepwise analysis of how XAI was created in current decision systems indicates that explainable models, in addition to increasing interpretability, can also help to improve debugging, bias detection and ethical AI deployment.
Meena Krishnan· International Journal of Mod...· 0 citations
Lucyde is introduced, a web-based demonstrator designed to help users explore, compare, and better understand XAI methods across different datasets, models, and configurations, and enables side-by-side comparison of methods and offers easy-to-understand supplementary information for different user groups.
Eda Ismail-Tsaous, Ute Schmid· Proceedings of the Thirty-Fi...· 0 citations
AI systems whose outputs inform real decisions, and increasingly consequential ones, require something that current documentation practice does not provide: a structured, inspectable representation of the knowledge they need to ground, contextualize, and reason about those decisions, ideally reviewed and signed off by...
Liliana Ferreira· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
