Experiencing Data w/ Brian T. O’Neill  (UX for AI Data Products, SAAS Analytics, Data Product Management) cover image

Experiencing Data w/ Brian T. O’Neill (UX for AI Data Products, SAAS Analytics, Data Product Management)

125 - Human-Centered XAI: Moving from Algorithms to Explainable ML UX with Microsoft Researcher Vera Liao

Sep 5, 2023
Vera Liao, Principal Researcher at Microsoft, discusses the importance of human-centered approach in rendering model explainability within a UI. She shares insights on why example-based explanations tend to out-perform feature-based ones and why traditional XAI methods may not be the solution for every explainability problem. Vera advocates for qualitative research in tandem with model work to improve outcomes and highlights the challenges of responsible AI.
44:42

Episode guests

Podcast summary created with Snipd AI

Quick takeaways

  • Explainability should be prioritized in AI applications to help users understand the system and make informed decisions.
  • A human-centered approach is crucial in developing effective explanations that align with user needs and enhance their understanding.

Deep dives

Importance of Explainability in AI Applications

Explainability should be at the core of AI applications to help users understand how the system works, what it can do, and how they can take appropriate actions. HCI researchers have been studying the topic of helping users understand for a long time, and explainability is an important component of that. It is crucial to consider users' mental models and provide explanations that can improve their understanding and decision-making process.

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner