4 papers
How Researchers Navigate Accountability, Transparency, and Trust When Using AI Tools in Early-Stage Research: A Think-Aloud Study
Sanjana Gautam, Houjiang Liu, Yujin Choi +1
In the early stages of scientific research, researchers rely on core scholarly judgments to identify relevant literature, assess credible evidence, and determine which directions m…
Who Owns Creativity and Who Does the Work? Trade-offs in LLM-Supported Research Ideation
Houjiang Liu, Yujin Choi, Sanjana Gautam +3
LLM-based agents offer new potential to accelerate science and reshape research work. However, the quality of researcher contributions can vary significantly depending on human abi…
Argumentative Experience: Reducing Confirmation Bias on Controversial Issues through LLM-Generated Multi-Persona Debates
Li Shi, Houjiang Liu, Yian Wong +4
Multi-persona debate systems powered by large language models (LLMs) show promise in reducing confirmation bias, which can fuel echo chambers and social polarization. However, empi…
Exploring Multidimensional Checkworthiness: Designing AI-assisted Claim Prioritization for Human Fact-checkers
Houjiang Liu, Jacek Gwizdka, Matthew Lease
Given the volume of potentially false claims online, claim prioritization is essential in allocating limited human resources available for fact-checking. In this study, we perceive…