Liang Gou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liang Gou has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Hongtao Hao
Bosch Research North America, United States
2 shared publications - Jiajing Guo
Cornell University, Ithaca, NY, USA
2 shared publications - Liu Ren
Bosch Research North America, Sunnyvale, USA
2 shared publications - Vikram Mohanty
Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, PA, USA
2 shared publications - Bei Jiang
Yunnan Key Laboratory of Screening and Research on Anti-Pathogenic Plant Resources from Western Yunnan, Institute of Materia Medica, College of Pharmacy, Dali University, Dali 671000, China
1 shared publication - Bo-Chao Liu
Yunnan Key Laboratory of Screening and Research on Anti-pathogenic Plant Resources from Western Yunnan, Dali University, Dali, People’s Republic of China
1 shared publication
Latest Publications
- 5 September 2024
- Published by Springer Nature in Revista Brasileira de Farmacognosia
- Vol. 34 (6) , 1377-1381
Flavonoids from Rhodiola fastigiata and their Antimalarial Activities
- 5 September 2024
- Published by Springer Nature in Revista Brasileira de Farmacognosia
- Vol. 34 (6) , 1377-1381
Flavonoids from Rhodiola fastigiata and their Antimalarial Activities
- Open Access
- 2 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Investigating Interaction Modes and User Agency in Human-LLM Collaboration for Domain-Specific Data Analysis
Despite demonstrating robust capabilities in performing tasks related to general-domain data-operation tasks, Large Language Models (LLMs) may exhibit shortcomings when applied to domain-specific tasks. We consider the design of domain-specific AI-powered data analysis tools from two dimensions: interaction and user agency. We implemented two design probes that fall on the two ends of the two dimensions: an open-ended high agency (OHA) prototype and a structured low agency (SLA) prototype. We conducted an interview study with nine data scientists to investigate (1) how users perceived the LLM outputs for data analysis assistance, and (2) how the two design probes, OHA and SLA, affected user behavior, performance, and perceptions. Our study revealed insights regarding participants’ interactions with LLMs, how they perceived the results, and their desire for explainability concerning LLM outputs, along with a noted need for collaboration with other users, and how they envisioned the utility of LLMs in their workflow.
- 2 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessInvestigating Interaction Modes and User Agency in Human-LLM Collaboration for Domain-Specific Data Analysis
Despite demonstrating robust capabilities in performing tasks related to general-domain data-operation tasks, Large Language Models (LLMs) may exhibit shortcomings when applied to domain-specific tasks. We consider the design of domain-specific AI-powered data analysis tools from two dimensions: interaction and user agency. We implemented two design probes that fall on the two ends of the two dimensions: an open-ended high agency (OHA) prototype and a structured low agency (SLA) prototype. We conducted an interview study with nine data scientists to investigate (1) how users perceived the LLM outputs for data analysis assistance, and (2) how the two design probes, OHA and SLA, affected user behavior, performance, and perceptions. Our study revealed insights regarding participants’ interactions with LLMs, how they perceived the results, and their desire for explainability concerning LLM outputs, along with a noted need for collaboration with other users, and how they envisioned the utility of LLMs in their workflow.
- Open Access
- 18 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 95-100
Can LLMs Infer Domain Knowledge from Code Exemplars? A Preliminary Study
- 18 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 95-100
Open AccessCan LLMs Infer Domain Knowledge from Code Exemplars? A Preliminary Study