14 citations · 21 across the 9 of their papers we have counts for
10 papers
Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation
Zoe De Simone, Angie Boggust, Fredo Durand +2
Text-to-image (T2I) systems enable rapid generation of high-fidelity imagery but are misaligned with how visual ideas develop. T2I systems generate outputs that make implicit visua…
Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language
Angie Boggust, Donghao Ren, Yannick Assogba +3
Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, natural language feature descriptions can be vague…
Quantifying Visualization Vibes: Measuring Socio-Indexicality at Scale
Amy Rae Fox, Michelle Morgenstern, Graham M. Jones +1
What impressions might readers form with visualizations that go beyond the data they encode? In this paper, we build on recent work that demonstrates the socio-indexical function o…
Visualization Vibes: The Socio-Indexical Function of Visualization Design
Michelle Morgenstern, Amy Rae Fox, Graham M. Jones +1
In contemporary information ecologies saturated with misinformation, disinformation, and a distrust of science itself, public data communication faces significant hurdles. Although…
Toward Cultural Interpretability: A Linguistic Anthropological Framework for Describing and Evaluating Large Language Models (LLMs)
Graham M. Jones, Shai Satran, Arvind Satyanarayan
This article proposes a new integration of linguistic anthropology and machine learning (ML) around convergent interests in both the underpinnings of language and making language t…
Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
Angie Boggust, Hyemin Bang, Hendrik Strobelt +1
While interpretability methods identify a model's learned concepts, they overlook the relationships between concepts that make up its abstractions and inform its ability to general…
DiffusionWorldViewer: Exposing and Broadening the Worldview Reflected by Generative Text-to-Image Models
Zoe De Simone, Angie Boggust, Arvind Satyanarayan +1
Generative text-to-image (TTI) models produce high-quality images from short textual descriptions and are widely used in academic and creative domains. Like humans, TTI models have…
Saliency Cards: A Framework to Characterize and Compare Saliency Methods
Angie Boggust, Harini Suresh, Hendrik Strobelt +2
Saliency methods are a common class of machine learning interpretability techniques that calculate how important each input feature is to a model's output. We find that, with the r…
Teaching Humans When To Defer to a Classifier via Exemplars
Hussein Mozannar, Arvind Satyanarayan, David Sontag
Expert decision makers are starting to rely on data-driven automated agents to assist them with various tasks. For this collaboration to perform properly, the human decision maker…
Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior
Angie Boggust, Benjamin Hoover, Arvind Satyanarayan +1
Saliency methods -- techniques to identify the importance of input features on a model's output -- are a common step in understanding neural network behavior. However, interpreting…