Schedule
Pre-Workshop Session: May 8th, 2024
All times listed in Eastern Time
11am-11:10am
Workshop Welcome
Welcome from the Organizers and Workshop Overview
11:10am-11:45am
Participant Talks
Three 8-10 minute talks from invited remote participants:
QuaLLM: An LLM-based Framework to Extract Quantitative Insights from Online Forums, presented by Varun Nagaraj Rao
Decoding Complexity: Exploring Human-AI Concordance in Qualitative Coding, presented by Elisabeth Kirsten
Large Language Models Cannot Replace Human Participants Because They Cannot Portray Identity Groups, presented by Angelina Wang
11:45am-12:15pm
Breakout Discussions
Participants introduce themselves and help shape the agenda for the workshop.
12:15-12:30
Group Synthesis
Group sharing and discussion
Main Workshop Day: May 12th, 2024
All times listed in Hawaii time
9:00 am - 9:45 am
Introduction to the Workshop
Keynote by Elena Glassman
Interfaces for Better Characterizing and Leveraging Large Language Models
Abstract: The behavior of a given large language model (LLM) is difficult to fully and globally characterize, due in large part to its large input and output spaces and enormous, often unspecified training data; their stochastic behavior can surprise users on previously seen and unseen inputs. And yet, even early on, their potential utility in data work was enticing. This talk will describe recent projects that help those wielding LLMs develop more local empirically grounded mental models of one or more LLMs' behavior. The talk will conclude with a discussion of interface design considerations and pitfalls to avoid when building LLM-powered features for assisting with data work.
Bio: Elena L. Glassman is currently an Assistant Professor of Computer Science at the Harvard Paulson School of Engineering & Applied Sciences, specializing in human-computer interaction. She was the Stanley A. Marks & William H. Marks Professor at the Radcliffe Institute for Advanced Study from 2018 - 2022, and more recently received a 2023 Sloan Research Fellowship. At MIT, she earned a PhD and MEng in Electrical Engineering and Computer Science and a BS in Electrical Science and Engineering, supported by the NSF Graduate Research Fellowship and the NDSEG Graduate Fellowship. Before joining Harvard, she was a postdoctoral scholar in Electrical Engineering and Computer Science at the University of California, Berkeley, where she received the Berkeley Institute for Data Science Moore/Sloan Data Science Fellowship.
9:45am - 10:20am
Intros and Icebreaker
Everyone introduces their work and participants participate in an icebreaker activity
Coffee Break 10:20am -11:00am
*Session 1: Gallery Opening*
How are HCI researchers using LLMs as research tools today?
11am-11:30am
Participant Talks
Three 8-10 minute talks from invited workshop participant speakers:
"Apprentices to Research Assistants: Advancing Research with Large Language Models" presented by Mohammad Namvarpour
"Practical Strategies for Labeling Qualitative Data Using Large Language Models" presented by Marianne Aubin Le Quéré
"Leveraging Large Language Models for Collective Decision-Making" presented by Chin-Chia Hsu
11:30am-12:05pm
Breakout Discussions
Discussions among participants, organized by methodological and/or research area, of past applications of LLMs to data work and challenges encountered
12:05pm-12:20pm
Group sharing
Group sharing and discussion
Lunch 12:20pm - 2pm
*Session 2: The Brushstrokes*
How can we empirically validate our new methodological tools?
2pm-2:30pm
Participant Talks: Empirical Evaluation
Three 10-minute talks from invited workshop participant speakers:
"Identifying Basic Human Values in Social Media Posts with Large Language Models" presented by Isabel Gallegos (Remote)
"A Brief Summary of the Study 'If in a Crowdsourced Data Annotation Pipeline, a GPT-4'" presented by Zeyu He
"AI-Mediated Annotation: Just put a human in the loop?" presented by Hope Schroeder
2:30pm-3:05pm
Breakout Discussions
Evaluation: methodological and empirical issues
3:05pm-3:20pm
Group Sharing
Evaluation: methodological and empirical issues
Afternoon Break 3:20 pm - 4 pm
*Session 3: Critical Reception*
Can we use LLMs as research tools ethically and thoughtfully?
4pm - 4:30pm
Participant Talks: Ethical + Critical Evaluation
Three 10-minute talks from invited workshop participant speakers:
"The Illusion of Artificial Inclusion" presented by Kevin R. McKee
"A Framework For Discussing LLMs as Tools for Qualitative Analysis" presented by James Eschrich
"Leveraging the Strengths of Qualitative Analysis to Improve Data Annotation" presented by Ruyuan Wan
4:30pm-5pm
Breakout Discussions
Evaluation: critical and ethical issues
5pm-5:20pm
Group Sharing and Final Remarks
Sharing evaluation strategies with the group
Optional Socializing 5:20 pm onwards