CHI 2024

ACM Conference on Human Factors in Computing Systems

The speed of computing innovation is faster than ever.
Research in human-computer interaction is part of this innovation and remains paramount to shaping our future technology frontier. Meet the Georgia Tech experts who are charting a path forward. #CHI2024

The ACM Computer-Human Interaction (CHI) Conference on Human Factors in Computing Systems has been the destination for global experts in Human-Computer Interaction (HCI) research for more than 30 years. Georgia Tech is a Top 10 contributor to the technical program, a record it has maintained for well over a decade. Discover the people who are leading HCI research in the era of artificial intelligence.

Opening Plenary

Georgia Tech at CHI 2024

Explore Georgia Tech’s experts and the organizations they are working with at CHI. Georgia Tech is a Top 10 institution based on the total papers and other research activity in the technical program.

Partner Organizations

Aalborg University • Accenture Labs • Art Center • California Institute of Technology • Carnegie Mellon University • Children’s Healthcare of Atlanta • Cluster Metaverse Lab • Cornell University • Costa Rican Institute of Technology • Drexel University • Emory University • Escuela Superior Politécnica del Litoral • Georgia Tech • Google • Harvard University • Hong Kong University of Science and Technology • Hugging Face • IBM Research • IIIT Delhi • Illumio • Indiana University • Integrated Design • Intel Labs • International Computer Science Institute • KAIST • Kennesaw State University • Kent State University • Lahore University of Management Sciences • Lucerne University of Applied Sciences and Arts • Meta • Microsoft • Mohammed VI Polytechnic University • Monterey Bay Aquarium Research Institute • Nokia Bell Labs • Northeastern University • Northern Arizona University • Northwestern University • NVIDIA • OMRON SINIC X • Palantir • Princeton University • PwC • Rensselaer Polytechnic Institute • Rochester Institute of Technology • Stanford University • Technische Hochschule Ingolstadt • The New York Times • The Pennsylvania State University • Tsinghua University • U.S. Department of Defense • Universiti Malaysia Pahang • University of Applied Sciences Upper Austria • University of California, Berkeley • University of California, Irvine • University of California, Santa Cruz • University of Cambridge • University of Chicago • University of Colorado Boulder • University of Edinburgh • University of Glasgow • University of Illinois at Urbana-Champaign • University of Maryland • University of Michigan • University of Notre Dame • University of Siegen • University of Texas, Austin • University of Washington • UX Indonesia • Vanderbilt University • Virginia Tech • William & Mary • Zucker Hillside Hospital

Faculty

Papers =

Other research activity =

Rosa Arriaga

Assoc. Professor, Interactive Computing

• •

Shaowen Bardzell

Professor, Interactive Computing

• •

Heidi Biggs

Research Scientist, Interactive Computing

Jay Bolter

Professor, Literature, Media, and Communication

Amy Bruckman

Professor, Interactive Computing

• •

Duen Horng Chau

Assoc. Professor, Computational Science and Engineering

• • • • •

Munmun De Choudhury

Assoc. Professor, Interactive Computing

Betsy DiSalvo

Assoc. Professor, Interactive Computing

Carl DiSalvo

Assoc. Professor, Interactive Computing

Alex Endert

Assoc. Professor, Interactive Computing

Ashok Goel

Professor, Interactive Computing

Noura Howell

Asst. Professor, Literature, Media, and Communication

• • •

Jennifer Kim

Asst. Professor, Interactive Computing

• •

Neha Kumar

Assoc. Professor, Interactive Computing

Christopher Le Dantec

Assoc. Professor, Interactive Computing

I-Hsiang “Ethan” Lee

Lecturer, Industrial and Systems Engineering

Christopher MacLellan

Asst. Professor, Interactive Computing

• • • • • •

Brian Magerko

Professor, Literature, Media, and Communication

Cassandra Naomi Monden

Research Scientist, Literature, Media, and Communication

Andrea Parker

Assoc. Professor, Interactive Computing

Elora Raymond

Asst. Professor, City and Regional Planning

Mark Riedl

Professor, Interactive Computing

Jessica Roberts

Asst. Professor, Interactive Computing

Abigale Stangl

Asst. Professor, Industrial Design

Thad Starner

Professor, Interactive Computing

• • • •

Anne Sullivan

Asst. Professor, Literature, Media, and Communication

Milka Trajkova

Research Scientist, Literature, Media, and Communication

Judith Uchidiuno

Asst. Professor, Interactive Computing

Lauren Wilcox

Adjunct Professor, Interactive Computing

• •

Richmond Wong

Asst. Professor, Literature, Media, and Communication

Yalong Yang

Asst. Professor, Interactive Computing

The Big Picture

Georgia Tech’s 33 papers in the technical program represent ~3 percent of conference papers. Our experts are also part of contributions to Alt Chi, Case Studies, Interactivity, Journals, Late-Breaking Work, Panels, Special Interest Groups, and Workshops.

Search for people and organizations in the chart below. The first column shows Georgia Tech-led teams. Each row is an entire team, with the label showing the first author’s name. Explore more now.

Explore Research

Georgia Tech faculty and students are participating across the CHI technical program. Explore their latest work and results. Total contributions to the papers program puts Georgia Tech in the Top 10 institutions for HCI research.

Body and Wellbeing

Vedant Das Swain, Lan Gao, Abhirup Mondal, Gregory Abowd, Munmun De Choudhury

Online Communities: Engagement

Koustuv Saha, Pranshu Gupta, Gloria Mark, Emre Kiciman, Munmun De Choudhury

User Studies on Large Language Models

Zijie Wang, Chinmay Kulkarni, Lauren Wilcox, Michael Terry, Michael Madaio

Jay Wang, lead author on one of Georgia Tech’s three award papers at CHI 2024. Photo by: Kevin Beasley/College of Computing

LLMs have empowered millions of people with diverse backgrounds, including writers, doctors, and educators, to build and prototype powerful AI apps through prompting. However, many of these AI prototypers don’t have training in computer science, let alone responsible AI practices.

Jay Wang, PhD student in Machine Learning

By Bryant Wine

Thanks to a Georgia Tech researcher’s new tool, application developers can now see potential harmful attributes in their prototypes.

Farsight is a tool designed for developers who use large language models (LLMs) to create applications powered by artificial intelligence (AI). Farsight alerts prototypers when they write LLM prompts that could be harmful and misused.

Downstream users can expect to benefit from better quality and safer products made with Farsight’s assistance. The tool’s lasting impact, though, is that it fosters responsible AI awareness by coaching developers on the proper use of LLMs.

Machine Learning Ph.D. candidate Zijie (Jay) Wang is Farsight’s lead architect. He will present the paper at the upcoming Conference on Human Factors in Computing Systems (CHI 2024). Farsight ranked in the top 5% of papers accepted to CHI 2024, earning it an honorable mention for the conference’s best paper award.

READ MORE

“LLMs have empowered millions of people with diverse backgrounds, including writers, doctors, and educators, to build and prototype powerful AI apps through prompting. However, many of these AI prototypers don’t have training in computer science, let alone responsible AI practices,” said Wang.

“With a growing number of AI incidents related to LLMs, it is critical to make developers aware of the potential harms associated with their AI applications.”

Wang referenced an example when two lawyers used ChatGPT to write a legal brief. A U.S. judge sanctioned the lawyers because their submitted brief contained six fictitious case citations that the LLM fabricated.

With Farsight, the group aims to improve developers’ awareness of responsible AI use. It achieves this by highlighting potential use cases, affected stakeholders, and possible harm associated with an application in the early prototyping stage.

A user study involving 42 prototypers showed that developers could better identify potential harms associated with their prompts after using Farsight. The users also found the tool more helpful and usable than existing resources.

Feedback from the study showed Farsight encouraged developers to focus on end-users and think beyond immediate harmful outcomes.

“While resources, like workshops and online videos, exist to help AI prototypers, they are often seen as tedious, and most people lack the incentive and time to use them,” said Wang.

“Our approach was to consolidate and display responsible AI resources in the same space where AI prototypers write prompts. In addition, we leverage AI to highlight relevant real-life incidents and guide users to potential harms based on their prompts.”

Farsight employs an in-situ user interface to show developers the potential negative consequences of their applications during prototyping.

Alert symbols for “neutral,” “caution,” and “warning” notify users when prompts require more attention. When a user clicks the alert symbol, an awareness sidebar expands from one side of the screen.

The sidebar shows an incident panel with actual news headlines from incidents relevant to the harmful prompt. The sidebar also has a use-case panel that helps developers imagine how different groups of people can use their applications in varying contexts.

Another key feature is the harm envisioner. This functionality takes a user’s prompt as input and assists them in envisioning potential harmful outcomes. The prompt branches into an interactive node tree that lists use cases, stakeholders, and harms, like “societal harm,” “allocative harm,” “interpersonal harm,” and more.

The novel design and insightful findings from the user study resulted in Farsight’s acceptance for presentation at CHI 2024.

CHI is considered the most prestigious conference for human-computer interaction and one of the top-ranked conferences in computer science.

CHI is affiliated with the Association for Computing Machinery. The conference takes place May 11-16 in Honolulu.

Wang worked on Farsight in Summer 2023 while interning at Google + AI Research group (PAIR).

Farsight’s co-authors from Google PAIR include Chinmay Kulkarni, Lauren Wilcox, Michael Terry, and Michael Madaio. The group possesses closer ties to Georgia Tech than just through Wang.

Terry, the current co-leader of Google PAIR, earned his Ph.D. in human-computer interaction from Georgia Tech in 2005. Madaio graduated from Tech in 2015 with a M.S. in digital media. Wilcox was a full-time faculty member in the School of Interactive Computing from 2013 to 2021 and serves in an adjunct capacity today.

Though not an author, one of Wang’s influences is his advisor, Polo Chau. Chau is an associate professor in the School of Computational Science and Engineering. His group specializes in data science, human-centered AI, and visualization research for social good. 

“I think what makes Farsight interesting is its unique in-workflow and human-AI collaborative approach,” said Wang.

“Furthermore, Farsight leverages LLMs to expand prototypers’ creativity and brainstorm a wide range of use cases, stakeholders, and potential harms.”

Many AI prototypers (A) from diverse backgrounds and roles use prompting tools (B) to prototype AI applications.
Farsight provides a range of in situ widgets for these tools,
helping AI prototypers envision the potential harms of their
AI applications during an early prototyping stage. Credit: Zijie J. Wang, et al.

A research team in the Ivan Allen College of Liberal Arts has expanded its Queer HCI scholarship, using queer theory to inform the design of wearable experiences that explore archives of gender and sexuality. The project, “Button Portraits,” invites individuals to listen to oral histories from prominent queer activists by pinning archival buttons to a wearable audio player, eliciting moving personal impressions.

The researchers observed 17 participants’ experiences with “Button Portraits,” and with semi-structured interviews, surfaced reflections on how the design evoked personal connections to history, queer self-identification, and relatability to archival materials. 

*the original story reported on an earlier version of the research project

Alexandra Teixeira Riggs
Alexandra Teixeira Riggs, PhD student in Digital Media

See you in Honolulu!

Development: College of Computing
Project Lead/Data Graphics: Joshua Preston
News: Nathan Deen, Bryant Wine
Web Data Management: Joni Isbell
Data: https://programs.sigchi.org/chi/2024 CC BY-NC-SA 4.0 DEED