Explainability
Making complex AI decisions understandable and justifiable to users.
20 papers carry this themeView in grid →
In these papers
- 01A Roadmap of Explainable Artificial Intelligence: Explain to Whom, When, What and How?Ziming Wang · 2024A disconnect persists across XAI research communities.
- 02Article LIME-Mine: Explainable Machine Learning for User Behavior Analysis in IoT ApplicationsXiaobo Cai · 2024Makes ML user-behaviour models interpretable.
- 03Predicting the Need for XAI from High-Granularity Interaction DataVagner Figueredo de Santana, Ana Fucs et al. · 2023Need for explainability across healthcare, finance, justice, recruiting.
- 04Explaining User Models with Different Levels of Detail for Transparent Recommendation: A User StudyMouadh Guesmi · 2022Explains user models at different levels of detail.
- 05Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and ValuesAlex Kale · 2022Asks how to act on interpretability findings, not just surface them.
- 06Anchoring Bias Affects Mental Model Formation and User Reliance in Explainable AI SystemsMahsan Nourani · 2021Cognitive (anchoring) bias distorts mental-model formation.
- 07On-demand Personalized Explanation for Transparent RecommendationMouadh Guesmi · 2021Addresses under-explored personalized explanation.
- 08Visual, textual or hybrid: the effect of user expertise on different explanationsMaxwell Szymanski · 2021The right explanation type depends on the end-user.
- 09Exploring Mental Models for Transparent and Controllable Recommender Systems: A Qualitative StudyThao Ngo · 2020Opacity hurts UX and perceived recommendation quality.
- 10Progressive Disclosure: When, Why, and How Do Users Want Algorithmic Transparency Information?Arron Springer, Steve Whittaker · 2020Progressive disclosure as a user-centric explanation strategy.
- 11Questioning the AI: Informing Design Practices for Explainable AI User ExperincesLiao · 2020Addresses real-world user needs for understanding AI.
- 12Personalized Explanations for Hybrid Recommender SystemsPigi Kouki · 2019Generating and visualizing explanations for hybrid models.
- 13To Explain or not to Explain: the Effects of Personal Characteristics when Explaining Music RecommendationsMartijn Millecamp · 2019Whether explaining helps depends on personal characteristics.
- 14Explanation in artificial intelligence: Insights from the social sciencesTim Miller · 2018Frames what makes an AI explanation satisfying to people.
- 15Explanations as Mechanisms for Supporting Algorithmic TransparencyEmilee Rader · 2018Studies specific explanation mechanisms, not just intended outcomes.
- 16Towards Algorithmic Experience: Initial Efforts for Social Media ContextsOscar Alvarado · 2018Needs tools to describe the experience of opaque algorithms.
- 17“Algorithms ruin everything”: #RIPTwitter, Folk Theories, and Resistance to Algorithmic Change in Social MediaDarren Gergle · 2017Inaccurate user understandings of how algorithmic systems work.
- 18User Preferences for Hybrid ExplanationsPigi Kouki · 2017Hybrid strategies are inherently harder to explain.
- 19Crowd-Based Personalized Natural Language Explanations for RecommendationsShuo Chang · 2016Overcomes simplistic algorithm-generated explanations using the crowd.
- 20How Much Information? Effects of Transparency on Trust in an Algorithmic InterfaceRene Kizilcec · 2016Asks how much information about the algorithm to expose.