Peiling Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Peiling Jiang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Haijun Xia
University of California San Diego, La Jolla, California, USA
7 shared publications - Fuling Sun
Department of Cognitive Science and Design Lab, University of California San Diego, United States
3 shared publications - Can Liu
School of Creative Media, City University of Hong Kong, Hong Kong, China
2 shared publications - Dishita Gdi Turakhia
Computer Science, Emory University, Atlanta, USA
2 shared publications - Li Feng
Computational Media and Arts Thrust, The Hong Kong University of Science and Technology (Guangzhou), China
2 shared publications - Stefanie Mueller
MIT CSAIL, Cambridge, Massachusetts, USA
2 shared publications
Latest Publications
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Orca: Browsing at Scale Through User-Driven and AI-Facilitated Orchestration Across Malleable Webpages
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-19
Open AccessOrca: Browsing at Scale Through User-Driven and AI-Facilitated Orchestration Across Malleable Webpages
- Top Cited PapersOpen Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Generative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Model
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Top Cited PapersOpen AccessGenerative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Model
- Open Access
- 10 September 2024
- Published by Knowledge Futures
Generating Reflection Prompts in Self-Directed Learning Activities with Generative AI
Self-reflection during maker activities is known to enhance conceptual comprehension and lead to better skill learning. While educational makerspaces commonly leverage reflective exercises guided by instructors, this practice often goes amiss in scenarios when makers interested in self-directed learning use online tutorials like Instructables. In this short paper, we explore the approach of using Large Language Models (LLMs), specifically OpenAI's GPT-4 for generating reflection prompts with the existing Instructable tutorials and aligning them with a list of learning goals adapted from prior work on maker skills learning. We built a system to generate Reflectables: Instructables designed for self-reflection while making. To exemplify the approach, we generated 9 Reflectables consisting of 128 prompts and evaluated them on seven attributes: goal-oriented, timely, contextual, sequential, multilevel, clear, and personalized. Our analysis highlights the benefits and limitations of this approach and points to further research directions for designing AI-based systems for reflection-focused self-directed learning in makerspaces.
- 10 September 2024
- Published by Knowledge Futures
Open AccessGenerating Reflection Prompts in Self-Directed Learning Activities with Generative AI
Self-reflection during maker activities is known to enhance conceptual comprehension and lead to better skill learning. While educational makerspaces commonly leverage reflective exercises guided by instructors, this practice often goes amiss in scenarios when makers interested in self-directed learning use online tutorials like Instructables. In this short paper, we explore the approach of using Large Language Models (LLMs), specifically OpenAI's GPT-4 for generating reflection prompts with the existing Instructable tutorials and aligning them with a list of learning goals adapted from prior work on maker skills learning. We built a system to generate Reflectables: Instructables designed for self-reflection while making. To exemplify the approach, we generated 9 Reflectables consisting of 128 prompts and evaluated them on seven attributes: goal-oriented, timely, contextual, sequential, multilevel, clear, and personalized. Our analysis highlights the benefits and limitations of this approach and points to further research directions for designing AI-based systems for reflection-focused self-directed learning in makerspaces.
- Open Access
- 31 October 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (ISS) , 463-482
1D-Touch: NLP-Assisted Coarse Text Selection via a Semi-Direct Gesture
Existing text selection techniques on touchscreen focus on improving the control for moving the carets. Coarse-grained text selection on word and phrase levels has not received much support beyond word-snapping and entity recognition. We introduce 1D-Touch, a novel text selection method that complements the carets-based sub-word selection by facilitating the selection of semantic units of words and above. This method employs a simple vertical slide gesture to expand and contract a selection area from a word. The expansion can be by words or by semantic chunks ranging from sub-phrases to sentences. This technique shifts the concept of text selection, from defining a range by locating the first and last words, towards a dynamic process of expanding and contracting a textual semantic entity. To understand the effects of our approach, we prototyped and tested two variants: WordTouch, which offers a straightforward word-by-word expansion, and ChunkTouch, which leverages NLP to chunk text into syntactic units, allowing the selection to grow by semantically meaningful units in response to the sliding gesture. Our evaluation, focused on the coarse-grained selection tasks handled by 1D-Touch, shows a 20% improvement over the default word-snapping selection method on Android.
- 31 October 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 7 (ISS) , 463-482
Open Access1D-Touch: NLP-Assisted Coarse Text Selection via a Semi-Direct Gesture
Existing text selection techniques on touchscreen focus on improving the control for moving the carets. Coarse-grained text selection on word and phrase levels has not received much support beyond word-snapping and entity recognition. We introduce 1D-Touch, a novel text selection method that complements the carets-based sub-word selection by facilitating the selection of semantic units of words and above. This method employs a simple vertical slide gesture to expand and contract a selection area from a word. The expansion can be by words or by semantic chunks ranging from sub-phrases to sentences. This technique shifts the concept of text selection, from defining a range by locating the first and last words, towards a dynamic process of expanding and contracting a textual semantic entity. To understand the effects of our approach, we prototyped and tested two variants: WordTouch, which offers a straightforward word-by-word expansion, and ChunkTouch, which leverages NLP to chunk text into syntactic units, allowing the selection to grow by semantically meaningful units in response to the sliding gesture. Our evaluation, focused on the coarse-grained selection tasks handled by 1D-Touch, shows a 20% improvement over the default word-snapping selection method on Android.
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Demonstrating 1D-Touch: NLP-Assisted Coarse Text Selection via a Semi-Direct Gesture
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessDemonstrating 1D-Touch: NLP-Assisted Coarse Text Selection via a Semi-Direct Gesture
- Top Cited PapersOpen Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-16
CrossTalk: Intelligent Substrates for Language-Oriented Interaction in Video-Based Communication and Collaboration
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Top Cited PapersOpen AccessCrossTalk: Intelligent Substrates for Language-Oriented Interaction in Video-Based Communication and Collaboration
- Top Cited PapersOpen Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Graphologue: Exploring Large Language Model Responses with Interactive Diagrams
Large language models (LLMs) have recently soared in popularity due to their ease of access and the unprecedented ability to synthesize text responses to diverse user questions. However, LLMs like ChatGPT present significant limitations in supporting complex information tasks due to the insufficient affordances of the text-based medium and linear conversational structure. Through a formative study with ten participants, we found that LLM interfaces often present long-winded responses, making it difficult for people to quickly comprehend and interact flexibly with various pieces of information, particularly during more complex tasks. We present Graphologue, an interactive system that converts text-based responses from LLMs into graphical diagrams to facilitate information-seeking and question-answering tasks. Graphologue employs novel prompting strategies and interface designs to extract entities and relationships from LLM responses and constructs node-link diagrams in real-time. Further, users can interact with the diagrams to flexibly adjust the graphical presentation and to submit context-specific prompts to obtain more information. Utilizing diagrams, Graphologue enables graphical, non-linear dialogues between humans and LLMs, facilitating information exploration, organization, and comprehension.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-20
Top Cited PapersOpen AccessGraphologue: Exploring Large Language Model Responses with Interactive Diagrams
Large language models (LLMs) have recently soared in popularity due to their ease of access and the unprecedented ability to synthesize text responses to diverse user questions. However, LLMs like ChatGPT present significant limitations in supporting complex information tasks due to the insufficient affordances of the text-based medium and linear conversational structure. Through a formative study with ten participants, we found that LLM interfaces often present long-winded responses, making it difficult for people to quickly comprehend and interact flexibly with various pieces of information, particularly during more complex tasks. We present Graphologue, an interactive system that converts text-based responses from LLMs into graphical diagrams to facilitate information-seeking and question-answering tasks. Graphologue employs novel prompting strategies and interface designs to extract entities and relationships from LLM responses and constructs node-link diagrams in real-time. Further, users can interact with the diagrams to flexibly adjust the graphical presentation and to submit context-specific prompts to obtain more information. Utilizing diagrams, Graphologue enables graphical, non-linear dialogues between humans and LLMs, facilitating information exploration, organization, and comprehension.
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
The Reflective Make-AR In-Action: Using Augmented Reality for Reflection-based Learning of Makerskills
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessThe Reflective Make-AR In-Action: Using Augmented Reality for Reflection-based Learning of Makerskills
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Log-it: Supporting Programming with Interactive, Contextual, Structured, and Visual Logs
Logging is a widely used technique for inspecting and understanding programs. However, the presentation of logs still often takes its ancient form of a linear stream of text that resides in a terminal, console, or log file. Despite its simplicity, interpreting log output is often challenging due to the large number of textual logs that lack structure and context. We conducted content analysis and expert interviews to understand the practices and challenges inherent in logging. These activities demonstrated that the current representation of logs does not provide the rich structures programmers need to interpret them or the program’s behavior. We present Log-it, a logging interface that enables programmers to interactively structure and visualize logs in situ. A user study with novices and experts showed that Log-it’s syntax and interface have a minimal learning curve, and the interactive representations and organizations of logs help programmers easily locate, synthesize, and understand logs.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-16
Open AccessLog-it: Supporting Programming with Interactive, Contextual, Structured, and Visual Logs
Logging is a widely used technique for inspecting and understanding programs. However, the presentation of logs still often takes its ancient form of a linear stream of text that resides in a terminal, console, or log file. Despite its simplicity, interpreting log output is often challenging due to the large number of textual logs that lack structure and context. We conducted content analysis and expert interviews to understand the practices and challenges inherent in logging. These activities demonstrated that the current representation of logs does not provide the rich structures programmers need to interpret them or the program’s behavior. We present Log-it, a logging interface that enables programmers to interactively structure and visualize logs in situ. A user study with novices and experts showed that Log-it’s syntax and interface have a minimal learning curve, and the interactive representations and organizations of logs help programmers easily locate, synthesize, and understand logs.
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Positional Control in Node-Based Programming
Visual programming languages enable novices to code with a lowered barrier. These languages typically employ one of two popular design approaches — block-based editing (e.g. Scratch), which allows users to control the execution order of code blocks, and node-based editing (e.g. Grasshopper), which enables users to control the data flow through nodes and wires. We propose integrating these two approaches by utilizing positional control in node-based programming to visualize and allow manipulation of both the execution order and data flow. A grid system organizes blocks and determines their sequence. Effect block is introduced, which controls other blocks within its effective range through positional constraints. As relocating blocks is easier than wiring that targets tiny inlets and outlets, we aim to shorten the feedback loop time and encourage exploration. We present b5, a web-based novel visual interface for creative coding, to demonstrate and evaluate this design.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessPositional Control in Node-Based Programming
Visual programming languages enable novices to code with a lowered barrier. These languages typically employ one of two popular design approaches — block-based editing (e.g. Scratch), which allows users to control the execution order of code blocks, and node-based editing (e.g. Grasshopper), which enables users to control the data flow through nodes and wires. We propose integrating these two approaches by utilizing positional control in node-based programming to visualize and allow manipulation of both the execution order and data flow. A grid system organizes blocks and determines their sequence. Effect block is introduced, which controls other blocks within its effective range through positional constraints. As relocating blocks is easier than wiring that targets tiny inlets and outlets, we aim to shorten the feedback loop time and encourage exploration. We present b5, a web-based novel visual interface for creative coding, to demonstrate and evaluate this design.