Towards Bidirectional Human-AI Alignment via Interaction: Human-Centered AI Explanation, Evaluation, and Development
Presented by Dr. Shen
Dr. Shen’s work anchors in HCI and intersects with multiple fields, such as NLP, ML, Speech Processing, and Data Science. Her research on bidirectional human-AI alignment aims to empower humans to interactively explain, evaluate, and collaborate with AI systems, while incorporating human feedback and values to improve AI systems.
Abstract
In this talk, Dr. Shen will provide a comprehensive overview of “bidirectional human-AI alignment,” starting with gaps in how humans understand AI decision-making. She will discuss why many explainable AI (XAI) algorithms fall short and introduce interactive solutions she developed to bridge this gap. Additionally, Dr. Shen will introduce methods for leveraging interactive human feedback to enhance AI performance. Finally, she will share insights from her latest research on fundamental values in alignment, outlining key challenges and opportunities for achieving bidirectional alignment over the long term.