We argue that one way to close the gap is to develop evaluation methods that account for different user requirements in these usage contexts.
Current literature and public discourse on "trust in AI" are often focused on the principles underlying trustworthy AI, with insufficient attention paid to how people develop trust.
Despite impressive performance in many benchmark datasets, AI models can still make mistakes, especially among out-of-distribution examples.
Using scenario-based design and question-driven XAI design approaches, we explore users' explainability needs for GenAI in three software engineering use cases: natural language to code, code translation, and code auto-completion.
Besides developing AI technologies for this purpose, the emerging field of human-AI decision making must embrace empirical approaches to form a foundational understanding of how humans interact and work with AI to make decisions.
In this chapter, we begin with a high-level overview of the technical landscape of XAI algorithms, then selectively survey our own and other recent HCI works that take human-centered approaches to design, evaluate, and provide conceptual and methodological tools for XAI.
no code implementations • 24 Sep 2021 • Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovic, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations.
In this paper, we conduct a mixed-methods study of how two different groups of whos--people with and without a background in AI--perceive different types of AI explanations.
In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models.
Automated Machine Learning (AutoML) is a rapidly growing set of technologies that automate the model development pipeline by searching model space and generating candidate models.
A pervasive design issue of AI systems is their explainability--how to provide appropriate information to help users understand the AI.
Data scientists face a steep learning curve in understanding a new domain for which they want to build machine learning (ML) models.
We suggested constitutive design elements of ST and developed a conceptual framework to unpack ST's effect and implications at the technical, decision-making, and organizational level.
There is an active research thread in AI, \autoai, that aims to develop systems for automating end-to-end the DS/ML Lifecycle.
no code implementations • 15 Nov 2020 • Umang Bhatt, Javier Antorán, Yunfeng Zhang, Q. Vera Liao, Prasanna Sattigeri, Riccardo Fogliato, Gabrielle Gauthier Melançon, Ranganath Krishnan, Jason Stanley, Omesh Tickoo, Lama Nachman, Rumi Chunara, Madhulika Srikumar, Adrian Weller, Alice Xiang
Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders.
no code implementations • • Kshitij Fadnis, Nathaniel Mills, Jatin Ganhotra, Haggai Roitman, Gaurav Pandey, Doron Cohen, Yosi Mass, Shai Erera, Chulaka Gunasekara, Danish Contractor, Siva Patel, Q. Vera Liao, Sachindra Joshi, Luis Lastras, David Konopnicki
Customer support agents play a crucial role as an interface between an organization and its end-users.
The similarity score between feature rankings provided by the annotator and the local model explanation is used to assign a weight to each corresponding committee model.
We conducted an empirical study comparing the model learning outcomes, feedback content and experience with XAL, to that of traditional AL and coactive learning (providing the model's prediction without the explanation).
In these scenarios, full automation is often undesirable, not only due to the significance of the outcome, but also because human experts can draw on their domain knowledge complementary to the model's to ensure task success.
Two general routes have been followed to develop artificial agents that are sensitive to human values---a top-down approach to encode values into the agents, and a bottom-up approach to learn from human actions, whether from real-world interactions or stories.
We introduce Doc2Dial, an end-to-end framework for generating conversational data grounded in business documents via crowdsourcing.
2 code implementations • 6 Sep 2019 • Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilović, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang
Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability.
The rise of increasingly more powerful chatbots offers a new way to collect information through conversational surveys, where a chatbot asks open-ended questions, interprets a user's free-text responses, and probes answers whenever needed.
no code implementations • 14 Dec 2018 • Neil Mallinar, Abhishek Shah, Rajendra Ugrani, Ayush Gupta, Manikandan Gurusankar, Tin Kam Ho, Q. Vera Liao, Yunfeng Zhang, Rachel K. E. Bellamy, Robert Yates, Chris Desmarais, Blake McGregor
We report on a user study that shows positive user feedback for this new approach to build conversational agents, and demonstrates the effectiveness of using data programming for auto-labeling.