Search Results - "Glassman, Elena L."

Towards More Effective AI-Assisted Programming: A Systematic Design Exploration to Improve Visual Studio IntelliCode's User Experience by Vaithilingam, Priyan, Glassman, Elena L., Groenwegen, Peter, Gulwani, Sumit, Henley, Austin Z., Malpani, Rohan, Pugh, David, Radhakrishna, Arjun, Soares, Gustavo, Wang, Joey, Yim, Aaron

“…AI-driven code editor extensions such as Visual Studio IntelliCode and Github CoPilot have become extremely popular. These tools recommend inserting chunks of…”
Get full text

A wavelet-like filter based on neuron action potentials for analysis of human scalp electroencephalographs by Glassman, E.L.

“…This paper describes the development and testing of a wavelet-like filter, named the SNAP, created from a neural activity simulation and used, in place of a…”
Get full text

DocMatrix: Self-teaching from multiple sources by Glassman, Elena L., Russell, Daniel M.

“…ABSTRACT Learners have a wealth of online resources to help them teach themselves new knowledge. However, not all resources are of equal quality or…”
Get full text

Revisiting Human-Robot Teaching and Learning Through the Lens of Human Concept Learning by Booth, Serena, Sharma, Sanjana, Chung, Sarah, Shah, Julie, Glassman, Elena L.

“…When interacting with a robot, humans form con-ceptual models (of varying quality) which capture how the robot behaves. These conceptual models form just from…”
Get full text

Designing Interfaces for Human-Computer Communication: An On-Going Collection of Considerations by Glassman, Elena L

“…While we do not always use words, communicating what we want to an AI is a conversation -- with ourselves as well as with it, a recurring loop with optional…”
Get full text

Reducing the Number of Channels for an Ambulatory Patient-Specific EEG-based Epileptic Seizure Detector by Applying Recursive Feature Elimination by Glassman, E.L., Guttag, J.V.

“…We are building an ambulatory version of a patient-specific epileptic seizure detector based on scalp EEG signals. Since patients have to wear the electrodes…”
Get full text

Imagining a Future of Designing with AI: Dynamic Grounding, Constructive Negotiation, and Sustainable Motivation by Vaithilingam, Priyan, Arawjo, Ian, Glassman, Elena L

“…We ideate a future design workflow that involves AI technology. Drawing from activity and communication theory, we attempt to isolate the new value large AI…”
Get full text

Antagonistic AI by Cai, Alice, Arawjo, Ian, Glassman, Elena L

“…The vast majority of discourse around AI development assumes that subservient, "moral" models aligned with "human values" are universally beneficial -- in…”
Get full text

The Usability of Pragmatic Communication in Regular Expression Synthesis by Vaithilingam, Priyan, Pu, Yewen, Glassman, Elena L

“…Programming-by-example (PBE) systems aim to alleviate the burden of programming. However, user-specified examples are often ambiguous, leaving multiple…”
Get full text

AI-Resilient Interfaces by Glassman, Elena L, Gu, Ziwei, Kummerfeld, Jonathan K

“…AI is powerful, but it can make choices that result in objective errors, contextually inappropriate outputs, and disliked options. We need AI-resilient…”
Get full text

DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing by Vaithilingam, Priyan, Glassman, Elena L, Inala, Jeevana Priya, Wang, Chenglong

“…Users often rely on GUIs to edit and interact with visualizations - a daunting task due to the large space of editing options. As a result, users are either…”
Get full text

Supporting Co-Adaptive Machine Teaching through Human Concept Learning and Cognitive Theories by Gebreegziabher, Simret Araya, Yang, Yukun, Glassman, Elena L, Li, Toby Jia-Jun

“…An important challenge in interactive machine learning, particularly in subjective or ambiguous domains, is fostering bi-directional alignment between humans…”
Get full text

Creative Writers' Attitudes on Writing as Training Data for Large Language Models by Gero, Katy Ilonka, Desai, Meera, Schnitzler, Carly, Eom, Nayun, Cushman, Jack, Glassman, Elena L

“…The use of creative writing as training data for large language models (LLMS) is highly contentious. While some argue that such use constitutes "fair use" and…”
Get full text

Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning by Gebreegziabher, Simret Araya, Ai, Kuangshi, Zhang, Zheng, Glassman, Elena L, Li, Toby Jia-Jun

“…Active Learning (AL) allows models to learn interactively from user feedback. This paper introduces a counterfactual data augmentation approach to AL,…”
Get full text

Supporting Sensemaking of Large Language Model Outputs at Scale by Gero, Katy Ilonka, Swoopes, Chelse, Gu, Ziwei, Kummerfeld, Jonathan K, Glassman, Elena L

“…Large language models (LLMs) are capable of generating multiple responses to a single prompt, yet little effort has been expended to help end-users or system…”
Get full text

An AI-Resilient Text Rendering Technique for Reading and Skimming Documents by Gu, Ziwei, Arawjo, Ian, Li, Kenneth, Kummerfeld, Jonathan K, Glassman, Elena L

“…Readers find text difficult to consume for many reasons. Summarization can address some of these difficulties, but introduce others, such as omitting,…”
Get full text

Metric Elicitation; Moving from Theory to Practice by Ali, Safinah, Upadhyay, Sohini, Hiranandani, Gaurush, Glassman, Elena L, Koyejo, Oluwasanmi

“…Metric Elicitation (ME) is a framework for eliciting classification metrics that better align with implicit user preferences based on the task and context. The…”
Get full text

Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems by Buçinca, Zana, Lin, Phoebe, Gajos, Krzysztof Z, Glassman, Elena L

“…Explainable artificially intelligent (XAI) systems form part of sociotechnical systems, e.g., human+AI teams tasked with making decisions. Yet, current XAI…”
Get full text

Evaluating the Interpretability of Generative Models by Interactive Reconstruction by Ross, Andrew Slavin, Chen, Nina, Hang, Elisa Zhao, Glassman, Elena L, Doshi-Velez, Finale

“…For machine learning models to be most useful in numerous sociotechnical systems, many have argued that they must be human-interpretable. However, despite…”
Get full text

Mudslide: A Spatially Anchored Census of Student Confusion for Online Lecture Videos by Glassman, Elena L, Kim, Juho, Monroy-Hernández, Andrés, Morris, Meredith Ringel

“…In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems (CHI 2015). ACM, New York, NY, USA, 1555-1564 Educators have developed…”
Get full text