Yoonjoo Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yoonjoo Lee has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Juho Kim
School of Computing, KAIST, Daejeon, Republic of Korea and SkillBench, Santa Barbara, California, USA
7 shared publications - Tae Soo Kim
School of Computing, KAIST, Daejeon, Republic of Korea
6 shared publications - Eytan Adar
University of Michigan
3 shared publications - Alexa Siu
Adobe Research, San Jose, California, USA
1 shared publication - April Yi Wang
ETH Zurich, Zurich, Switzerland
1 shared publication - Bjoern Hartmann
University of California, Berkeley, Berkeley, CA, USA
1 shared publication
Latest Publications
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Revibing HCI: Agentic Reimplementation as Community Practice
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessRevibing HCI: Agentic Reimplementation as Community Practice
- Open Access
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Revibing Code from Papers: Reimplementing HCI Artifacts
- 2 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessRevibing Code from Papers: Reimplementing HCI Artifacts
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-27
Evalet: Evaluating Large Language Models through Functional Fragmentation
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-27
Open AccessEvalet: Evaluating Large Language Models through Functional Fragmentation
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
DocVoyager: Anticipating User’s Information Needs and Guiding Document Reading through Question Answering
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessDocVoyager: Anticipating User’s Information Needs and Guiding Document Reading through Question Answering
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 2518-2531
One vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations
As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately, most LLM-powered systems resort to single results which, correct or not, users accept. Having the LLM produce multiple outputs may help identify disagreements or alternatives. However, it is not obvious how the user will interpret conflicts or inconsistencies. To this end, we investigate how users perceive the AI model and comprehend the generated information when they receive multiple, potentially inconsistent, outputs. Through a preliminary study, we identified five types of output inconsistencies. Based on these categories, we conducted a study (N = 252) in which participants were given one or more LLM-generated passages to an information-seeking question. We found that inconsistency within multiple LLM-generated outputs lowered the participants’ perceived AI capacity, while also increasing their comprehension of the given information. Specifically, we observed that this positive effect of inconsistencies was most significant for participants who read two passages, compared to those who read three. Based on these findings, we present design implications that, instead of regarding LLM output inconsistencies as a drawback, we can reveal the potential inconsistencies to transparently indicate the limitations of these models and promote critical LLM usage.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 2518-2531
Open AccessOne vs. Many: Comprehending Accurate Information from Multiple Erroneous and Inconsistent AI Generations
As Large Language Models (LLMs) are nondeterministic, the same input can generate different outputs, some of which may be incorrect or hallucinated. If run again, the LLM may correct itself and produce the correct answer. Unfortunately, most LLM-powered systems resort to single results which, correct or not, users accept. Having the LLM produce multiple outputs may help identify disagreements or alternatives. However, it is not obvious how the user will interpret conflicts or inconsistencies. To this end, we investigate how users perceive the AI model and comprehend the generated information when they receive multiple, potentially inconsistent, outputs. Through a preliminary study, we identified five types of output inconsistencies. Based on these categories, we conducted a study (N = 252) in which participants were given one or more LLM-generated passages to an information-seeking question. We found that inconsistency within multiple LLM-generated outputs lowered the participants’ perceived AI capacity, while also increasing their comprehension of the given information. Specifically, we observed that this positive effect of inconsistencies was most significant for participants who read two passages, compared to those who read three. Based on these findings, we present design implications that, instead of regarding LLM output inconsistencies as a drawback, we can reveal the potential inconsistencies to transparently indicate the limitations of these models and promote critical LLM usage.
- Top Cited PapersOpen Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-21
EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-21
Top Cited PapersOpen AccessEvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-26
VIVID: Human-AI Collaborative Authoring of Vicarious Dialogues from Lecture Videos
The lengthy monologue-style online lectures cause learners to lose engagement easily. Designing lectures in a “vicarious dialogue” format can foster learners’ cognitive activities more than monologue-style. However, designing online lectures in a dialogue style catered to the diverse needs of learners is laborious for instructors. We conducted a design workshop with eight educational experts and seven instructors to present key guidelines and the potential use of large language models (LLM) to transform a monologue lecture script into pedagogically meaningful dialogue. Applying these design guidelines, we created VIVID which allows instructors to collaborate with LLMs to design, evaluate, and modify pedagogical dialogues. In a within-subjects study with instructors (N=12), we show that VIVID helped instructors select and revise dialogues efficiently, thereby supporting the authoring of quality dialogues. Our findings demonstrate the potential of LLMs to assist instructors with creating high-quality educational dialogues across various learning stages.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-26
Open AccessVIVID: Human-AI Collaborative Authoring of Vicarious Dialogues from Lecture Videos
The lengthy monologue-style online lectures cause learners to lose engagement easily. Designing lectures in a “vicarious dialogue” format can foster learners’ cognitive activities more than monologue-style. However, designing online lectures in a dialogue style catered to the diverse needs of learners is laborious for instructors. We conducted a design workshop with eight educational experts and seven instructors to present key guidelines and the potential use of large language models (LLM) to transform a monologue lecture script into pedagogically meaningful dialogue. Applying these design guidelines, we created VIVID which allows instructors to collaborate with LLMs to design, evaluate, and modify pedagogical dialogues. In a within-subjects study with instructors (N=12), we show that VIVID helped instructors select and revise dialogues efficiently, thereby supporting the authoring of quality dialogues. Our findings demonstrate the potential of LLMs to assist instructors with creating high-quality educational dialogues across various learning stages.
- Open Access
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-19
PaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers
With the rapid growth of scholarly archives, researchers subscribe to “paper alert’’ systems that periodically provide them with recommendations of recently published papers that are similar to previously collected papers. However, researchers sometimes struggle to make sense of nuanced connections between recommended papers and their own research context, as existing systems only present paper titles and abstracts. To help researchers spot these connections, we present PaperWeaver, an enriched paper alerts system that provides contextualized text descriptions of recommended papers based on user-collected papers. PaperWeaver employs a computational method based on Large Language Models (LLMs) to infer users’ research interests from their collected papers, extract context-specific aspects of papers, and compare recommended and collected papers on these aspects. Our user study (N=15) showed that participants using PaperWeaver were able to better understand the relevance of recommended papers and triage them more confidently when compared to a baseline that presented the related work sections from recommended papers.
- 11 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessPaperWeaver: Enriching Topical Paper Alerts by Contextualizing Recommended Papers with User-collected Papers
With the rapid growth of scholarly archives, researchers subscribe to “paper alert’’ systems that periodically provide them with recommendations of recently published papers that are similar to previously collected papers. However, researchers sometimes struggle to make sense of nuanced connections between recommended papers and their own research context, as existing systems only present paper titles and abstracts. To help researchers spot these connections, we present PaperWeaver, an enriched paper alerts system that provides contextualized text descriptions of recommended papers based on user-collected papers. PaperWeaver employs a computational method based on Large Language Models (LLMs) to infer users’ research interests from their collected papers, extract context-specific aspects of papers, and compare recommended and collected papers on these aspects. Our user study (N=15) showed that participants using PaperWeaver were able to better understand the relevance of recommended papers and triage them more confidently when compared to a baseline that presented the related work sections from recommended papers.
- Top Cited PapersOpen Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Cells, Generators, and Lenses: Design Framework for Object-Oriented Interaction with Large Language Models
Large Language Models (LLMs) have become the backbone of numerous writing interfaces with the goal of supporting end-users across diverse writing tasks. While LLMs reduce the effort of manual writing, end-users may need to experiment and iterate with various generation configurations (e.g., inputs and model parameters) until results meet their goals. However, these interfaces are not designed for experimentation and iteration, and can restrict how end-users track, compare, and combine configurations. In this work, we present “cells, generators, and lenses”, a framework to designing interfaces that support interactive objects that embody configuration components (i.e., input, model, output). Interface designers can apply our framework to produce interfaces that enable end-users to create variations of these objects, combine and recombine them into new configurations, and compare them in parallel to efficiently iterate and experiment with LLMs. To showcase how our framework generalizes to diverse writing tasks, we redesigned three different interfaces—story writing, copywriting, and email composing—and, to demonstrate its effectiveness in supporting end-users, we conducted a comparative study (N=18) where participants used our interactive objects to generate and experiment more. Finally, we investigate the usability of the framework through a workshop with designers (N=3) where we observed that our framework served as both bootstrapping and inspiration in the design process.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-18
Top Cited PapersOpen AccessCells, Generators, and Lenses: Design Framework for Object-Oriented Interaction with Large Language Models
Large Language Models (LLMs) have become the backbone of numerous writing interfaces with the goal of supporting end-users across diverse writing tasks. While LLMs reduce the effort of manual writing, end-users may need to experiment and iterate with various generation configurations (e.g., inputs and model parameters) until results meet their goals. However, these interfaces are not designed for experimentation and iteration, and can restrict how end-users track, compare, and combine configurations. In this work, we present “cells, generators, and lenses”, a framework to designing interfaces that support interactive objects that embody configuration components (i.e., input, model, output). Interface designers can apply our framework to produce interfaces that enable end-users to create variations of these objects, combine and recombine them into new configurations, and compare them in parallel to efficiently iterate and experiment with LLMs. To showcase how our framework generalizes to diverse writing tasks, we redesigned three different interfaces—story writing, copywriting, and email composing—and, to demonstrate its effectiveness in supporting end-users, we conducted a comparative study (N=18) where participants used our interactive objects to generate and experiment more. Finally, we investigate the usability of the framework through a workshop with designers (N=3) where we observed that our framework served as both bootstrapping and inspiration in the design process.
- Top Cited PapersOpen Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-22
DAPIE: Interactive Step-by-Step Explanatory Dialogues to Answer Children’s Why and How Questions
Children acquire an understanding of the world by asking “why” and “how” questions. Conversational agents (CAs) like smart speakers or voice assistants can be promising respondents to children’s questions as they are more readily available than parents or teachers. However, CAs’ answers to “why” and “how” questions are not designed for children, as they can be difficult to understand and provide little interactivity to engage the child. In this work, we propose design guidelines for creating interactive dialogues that promote children’s engagement and help them understand explanations. Applying these guidelines, we propose DAPIE, a system that answers children’s questions through interactive dialogue by employing an AI-based pipeline that automatically transforms existing long-form answers from online sources into such dialogues. A user study (N=16) showed that, with DAPIE, children performed better in an immediate understanding assessment while also reporting higher enjoyment than when explanations were presented sentence-by-sentence.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-22
Top Cited PapersOpen AccessDAPIE: Interactive Step-by-Step Explanatory Dialogues to Answer Children’s Why and How Questions
Children acquire an understanding of the world by asking “why” and “how” questions. Conversational agents (CAs) like smart speakers or voice assistants can be promising respondents to children’s questions as they are more readily available than parents or teachers. However, CAs’ answers to “why” and “how” questions are not designed for children, as they can be difficult to understand and provide little interactivity to engage the child. In this work, we propose design guidelines for creating interactive dialogues that promote children’s engagement and help them understand explanations. Applying these guidelines, we propose DAPIE, a system that answers children’s questions through interactive dialogue by employing an AI-based pipeline that automatically transforms existing long-form answers from online sources into such dialogues. A user study (N=16) showed that, with DAPIE, children performed better in an immediate understanding assessment while also reporting higher enjoyment than when explanations were presented sentence-by-sentence.