Even if explanations: Prior work, desiderata & benchmarks for semi-factual xai
Recently, eXplainable AI (XAI) research has focused on counterfactual explanations as post-
hoc justifications for AI-system decisions (eg a customer refused a loan might be told: If you …
hoc justifications for AI-system decisions (eg a customer refused a loan might be told: If you …
The Utility of “Even if” semifactual explanation to optimise positive outcomes
When users receive either a positive or negative outcome from an automated system,
Explainable AI (XAI) has almost exclusively focused on how to mutate negative outcomes …
Explainable AI (XAI) has almost exclusively focused on how to mutate negative outcomes …
Even-Ifs from If-Onlys: Are the Best Semi-factual Explanations Found Using Counterfactuals as Guides?
Recently, counterfactuals using “if-only” explanations have become very popular in
eXplainable AI (XAI), as they describe which changes to feature-inputs of a black-box AI …
eXplainable AI (XAI), as they describe which changes to feature-inputs of a black-box AI …
Evaluating clinical diversity and plausibility of synthetic capsule endoscopic images
Abstract Wireless Capsule Endoscopy (WCE) is being increasingly used as an alternative
imaging modality for complete and non-invasive screening of the gastrointestinal tract …
imaging modality for complete and non-invasive screening of the gastrointestinal tract …
Semi-factual Explanations in AI
S Aryal - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Most of the recent works on post-hoc example-based eXplainable AI (XAI) methods revolves
around employing counterfactual explanations to provide justification of the predictions …
around employing counterfactual explanations to provide justification of the predictions …
Learning from Semi-Factuals: A Debiased and Semantic-Aware Framework for Generalized Relation Discovery
We introduce a novel task, called Generalized Relation Discovery (GRD), for open-world
relation extraction. GRD aims to identify unlabeled instances in existing pre-defined …
relation extraction. GRD aims to identify unlabeled instances in existing pre-defined …
Semantic Map Guided Synthesis of Wireless Capsule Endoscopy Images using Diffusion Models
Wireless capsule endoscopy (WCE) is a non-invasive method for visualizing the
gastrointestinal (GI) tract, crucial for diagnosing GI tract diseases. However, interpreting …
gastrointestinal (GI) tract, crucial for diagnosing GI tract diseases. However, interpreting …
iSee: Advancing Multi-Shot Explainable AI Using Case-Based Recommendations
Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-
making processes. Recent findings suggest that a single explainer may not meet the diverse …
making processes. Recent findings suggest that a single explainer may not meet the diverse …
[PDF][PDF] Testing Most Distant Neighbor (MDN) Variants for Semi-Factual Explanations in XAI
Recently, Semi-factual explanations have gained popularity in the eXplainable AI (XAI)
community. They provide “even if" justifications to indicate what key input features could …
community. They provide “even if" justifications to indicate what key input features could …