Yihan Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yihan Liu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Luoxuan Weng
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, Zhejiang, China
2 shared publications - Wei Chen
Zhejiang University, Hangzhou, Zhejiang, China
2 shared publications Danqing Huang
Tencent Inc., Shenzhen, China
1 shared publicationHaozhe Feng
Tencent Inc., Shenzhen, China
1 shared publicationJunyu Lu
State Key Lab of CADCG, Zhejiang University, Hangzhou, China
1 shared publication- Ollie Woodman
State Key Lab of CADCG, Zhejiang University, Hangzhou, China
1 shared publication
Latest Publications
- Top Cited Papers
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (6) , 3719-3732
InsightLens: Augmenting LLM-Powered Data Analysis With Interactive Insight Management and Navigation
The proliferation of large language models (LLMs) has revolutionized the capabilities of natural language interfaces (NLIs) for data analysis. LLMs can perform multi-step and complex reasoning to generate data insights based on users' analytic intents. However, these insights often entangle with an abundance of contexts in analytic conversations such as code, visualizations, and natural language explanations. This hinders efficient recording, organization, and navigation of insights within the current chat-based LLM interfaces. In this paper, we first conduct a formative study with eight data analysts to understand their general workflow and pain points of insight management during LLM-powered data analysis. Accordingly, we introduce InsightLens, an interactive system to overcome such challenges. Built upon an LLM-agent-based framework that automates insight recording and organization along with the analysis process, InsightLens visualizes the complex conversational contexts from multiple aspects to facilitate insight navigation. A user study with twelve data analysts demonstrates the effectiveness of InsightLens, showing that it significantly reduces users' manual and cognitive effort without disrupting their conversational data analysis workflow, leading to a more efficient analysis experience.
- 6 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (6) , 3719-3732
Top Cited PapersInsightLens: Augmenting LLM-Powered Data Analysis With Interactive Insight Management and Navigation
The proliferation of large language models (LLMs) has revolutionized the capabilities of natural language interfaces (NLIs) for data analysis. LLMs can perform multi-step and complex reasoning to generate data insights based on users' analytic intents. However, these insights often entangle with an abundance of contexts in analytic conversations such as code, visualizations, and natural language explanations. This hinders efficient recording, organization, and navigation of insights within the current chat-based LLM interfaces. In this paper, we first conduct a formative study with eight data analysts to understand their general workflow and pain points of insight management during LLM-powered data analysis. Accordingly, we introduce InsightLens, an interactive system to overcome such challenges. Built upon an LLM-agent-based framework that automates insight recording and organization along with the analysis process, InsightLens visualizes the complex conversational contexts from multiple aspects to facilitate insight navigation. A user study with twelve data analysts demonstrates the effectiveness of InsightLens, showing that it significantly reduces users' manual and cognitive effort without disrupting their conversational data analysis workflow, leading to a more efficient analysis experience.
- 14 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (9) , 4761-4775
SPROUT: An Interactive Authoring Tool for Generating Programming Tutorials With the Visualization of Large Language Models
The rapid development of large language models (LLMs), such as ChatGPT, has revolutionized the efficiency of creating programming tutorials. LLMs can be instructed with text prompts to generate comprehensive text descriptions for code snippets provided by users. However, the lack of transparency in the end-to-end generation process has hindered the understanding of model behavior and limited user control over the generated results. To tackle this challenge, we introduce a novel approach that breaks down the programming tutorial creation task into actionable steps. By employing the tree-of-thought method, LLMs engage in an exploratory process to generate diverse and faithful programming tutorials. We then present SPROUT, an authoring tool equipped with a series of interactive visualizations that empower users to have greater control and understanding of the programming tutorial creation process. A formal user study demonstrated the effectiveness of SPROUT, showing that our tool assists users to actively participate in the programming tutorial creation process, leading to more reliable and customizable results. By providing users with greater control and understanding, SPROUT enhances the user experience and improves the overall quality of programming tutorial.
- 14 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 31 (9) , 4761-4775
SPROUT: An Interactive Authoring Tool for Generating Programming Tutorials With the Visualization of Large Language Models
The rapid development of large language models (LLMs), such as ChatGPT, has revolutionized the efficiency of creating programming tutorials. LLMs can be instructed with text prompts to generate comprehensive text descriptions for code snippets provided by users. However, the lack of transparency in the end-to-end generation process has hindered the understanding of model behavior and limited user control over the generated results. To tackle this challenge, we introduce a novel approach that breaks down the programming tutorial creation task into actionable steps. By employing the tree-of-thought method, LLMs engage in an exploratory process to generate diverse and faithful programming tutorials. We then present SPROUT, an authoring tool equipped with a series of interactive visualizations that empower users to have greater control and understanding of the programming tutorial creation process. A formal user study demonstrated the effectiveness of SPROUT, showing that our tool assists users to actively participate in the programming tutorial creation process, leading to more reliable and customizable results. By providing users with greater control and understanding, SPROUT enhances the user experience and improves the overall quality of programming tutorial.