All

Papers

Browse and search HCI research papers from All

Active Filters

Author: 7828

11 results

Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors

AI policy sets boundaries on acceptable behavior for AI models, but this is challenging in the context of large language models (LLMs): how do you ensure coverage over a vast behavior space? We introduce policy maps, an approach to AI policy design inspired by the practice of physical mapmaking. Instead of aiming for…

Michelle S. Lam et al.Stanford University

Exploring Empty Spaces: Human-in-the-Loop Data Augmentation

Data augmentation is crucial to make machine learning models more robust and safe. However, augmenting data can be challenging as it requires generating diverse data points to rigorously evaluate model behavior on edge cases and mitigate potential harms. Creating high-quality augmentations that cover these "unknown un…

Catherine Yeh et al.Harvard University

InterLink: Linking Text with Code and Output in Computational Notebooks

Computational notebooks, widely used for ad-hoc analysis and often shared with others, can be difficult to understand because the standard linear layout is not optimized for reading. In particular, related text, code, and outputs may be spread across the UI making it difficult to draw connections. In response, we intr…

Yanna Lin et al.Hong Kong University of Science and Technology

Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences

On-device machine learning (ML) promises to improve the privacy, responsiveness, and proliferation of new, intelligent user experiences by moving ML computation onto everyday personal devices. However, today's large ML models must be drastically compressed to run efficiently on-device, a hurtle that requires deep, yet…

Fred Hohman et al.Apple

AdRecommended

Learn AI Coding at CodeNow

Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work.

Explore Now

Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference

On-device machine learning (ML) moves computation from the cloud to personal devices, protecting user privacy and enabling intelligent user experiences. However, fitting models on devices with limited resources presents a major technical challenge: practitioners need to optimize models and balance hardware metrics suc…

Fred Hohman et al.Apple

VegaProf: Profiling Vega Visualizations

Domain-specific languages (DSLs) for visualization aim to facilitate visualization creation by providing abstractions that offload implementation and execution details from users to the system layer. Therefore, DSLs often execute user-defined specifications by transforming them into intermediate representations (IRs)…

Junran Yang et al.University Of Washington

Angler: Helping Machine Translation Practitioners Prioritize Model Improvements

Machine learning (ML) models can fail in unexpected ways in the real world, but not all model failures are equal. With finite time and resources, ML practitioners are forced to prioritize their model debugging and improvement efforts. Through interviews with 13 ML practitioners at Apple, we found that practitioners co…

Samantha Robertson et al.University of California

ComputableViz: Mathematical Operators as a Formalism for Visualization Processing and Analysis

Data visualizations are created and shared on the web at an unprecedented speed, raising new needs and questions for processing and analyzing visualizations after they have been generated and digitized. However, existing formalisms focus on operating on a single visualization instead of multiple visualizations, making…

Aoyu Wu et al.Hong Kong University of Science and Technology

Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels

The confusion matrix, a ubiquitous visualization for helping people evaluate machine learning models, is a tabular layout that compares predicted class labels against actual class labels over all data instances. We conduct formative research with machine learning practitioners at Apple and find that conventional confu…

Jochen Görtler et al.University of Konstanz

Symphony: Composing Interactive Interfaces for Machine Learning

Interfaces for machine learning (ML), information and visualizations about models or data, can help practitioners build robust and responsible ML systems. Despite their benefits, recent studies of ML teams and our interviews with practitioners (n=9) showed that ML interfaces have limited adoption in practice. While ex…

Alex Bäuerle et al.Sigma Computing

mage: Fluid Moves Between Code and Graphical Work in Computational Notebooks

We aim to increase the flexibility at which a data worker can choose the right tool for the job, regardless of whether the tool is a code library or an interactive graphical user interface (GUI). To achieve this flexibility, we extend computational notebooks with a new API mage, which supports tools that can represent…

Mary Beth Kery et al.Carnegie Mellon University

Paper Title	Authors	Research Topics	Paper Database	Year
Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors AI policy sets boundaries on acceptable behavior for AI models, but this is challenging in the context of large language models (LLMs): how do you ensure coverage over a vast behavior space? We introduce policy maps, an approach to AI policy design inspired by the practice of physical mapmaking. Instead of aiming for…	ML Michelle S. Lam et al.Stanford University
emoji_events Exploring Empty Spaces: Human-in-the-Loop Data Augmentation Data augmentation is crucial to make machine learning models more robust and safe. However, augmenting data can be challenging as it requires generating diverse data points to rigorously evaluate model behavior on edge cases and mitigate potential harms. Creating high-quality augmentations that cover these "unknown un…	CY Catherine Yeh et al.Harvard University
InterLink: Linking Text with Code and Output in Computational Notebooks Computational notebooks, widely used for ad-hoc analysis and often shared with others, can be difficult to understand because the standard linear layout is not optimized for reading. In particular, related text, code, and outputs may be spread across the UI making it difficult to draw connections. In response, we intr…	YL Yanna Lin et al.Hong Kong University of Science and Technology
Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences On-device machine learning (ML) promises to improve the privacy, responsiveness, and proliferation of new, intelligent user experiences by moving ML computation onto everyday personal devices. However, today's large ML models must be drastically compressed to run efficiently on-device, a hurtle that requires deep, yet…	FH Fred Hohman et al.Apple
AdRecommended Learn AI Coding at CodeNow Structured lessons, hands-on projects, and continuous updates for people bringing AI into real development work. Explore Now
emoji_events Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference On-device machine learning (ML) moves computation from the cloud to personal devices, protecting user privacy and enabling intelligent user experiences. However, fitting models on devices with limited resources presents a major technical challenge: practitioners need to optimize models and balance hardware metrics suc…	FH Fred Hohman et al.Apple
VegaProf: Profiling Vega Visualizations Domain-specific languages (DSLs) for visualization aim to facilitate visualization creation by providing abstractions that offload implementation and execution details from users to the system layer. Therefore, DSLs often execute user-defined specifications by transforming them into intermediate representations (IRs)…	JY Junran Yang et al.University Of Washington
Angler: Helping Machine Translation Practitioners Prioritize Model Improvements Machine learning (ML) models can fail in unexpected ways in the real world, but not all model failures are equal. With finite time and resources, ML practitioners are forced to prioritize their model debugging and improvement efforts. Through interviews with 13 ML practitioners at Apple, we found that practitioners co…	SR Samantha Robertson et al.University of California
ComputableViz: Mathematical Operators as a Formalism for Visualization Processing and Analysis Data visualizations are created and shared on the web at an unprecedented speed, raising new needs and questions for processing and analyzing visualizations after they have been generated and digitized. However, existing formalisms focus on operating on a single visualization instead of multiple visualizations, making…	AW Aoyu Wu et al.Hong Kong University of Science and Technology
emoji_events Neo: Generalizing Confusion Matrix Visualization to Hierarchical and Multi-Output Labels The confusion matrix, a ubiquitous visualization for helping people evaluate machine learning models, is a tabular layout that compares predicted class labels against actual class labels over all data instances. We conduct formative research with machine learning practitioners at Apple and find that conventional confu…	JG Jochen Görtler et al.University of Konstanz
Symphony: Composing Interactive Interfaces for Machine Learning Interfaces for machine learning (ML), information and visualizations about models or data, can help practitioners build robust and responsible ML systems. Despite their benefits, recent studies of ML teams and our interviews with practitioners (n=9) showed that ML interfaces have limited adoption in practice. While ex…	AB Alex Bäuerle et al.Sigma Computing
mage: Fluid Moves Between Code and Graphical Work in Computational Notebooks We aim to increase the flexibility at which a data worker can choose the right tool for the job, regardless of whether the tool is a code library or an interactive graphical user interface (GUI). To achieve this flexibility, we extend computational notebooks with a new API mage, which supports tools that can represent…	MK Mary Beth Kery et al.Carnegie Mellon University