66 citations · 69 across the 6 of their papers we have counts for
7 papers
What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media
Zifan Peng, Yini Huang, Aiwen Lu +7
Public social media posts can reveal private information through weak cues scattered across text, images, or metadata. Such leakage is often cumulative and cross-post: cues that ap…
Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines
Peixian Zhang, Qiming Ye, Zifan Peng +2
LLM-based Search Engines (LLM-SEs) introduces a new paradigm for information seeking. Unlike Traditional Search Engines (TSEs) (e.g., Google), these systems summarize results, ofte…
Benchmarking and Understanding Safety Risks in AI Character Platforms
Yiluo Wei, Peixian Zhang, Gareth Tyson
AI character platforms, which allow users to engage in conversations with AI personas, are a rapidly growing application domain. However, their immersive and personalized nature, c…
Exploring the Capability of ChatGPT to Reproduce Human Labels for Social Computing Tasks (Extended Version)
Yiming Zhu, Peixian Zhang, Ehsan-Ul Haq +2
Harnessing the potential of large language models (LLMs) like ChatGPT can help address social challenges through inclusive, ethical, and sustainable means. In this paper, we invest…
The Emergence of Threads: The Birth of a New Social Network
Peixian Zhang, Yupeng He, Ehsan-Ul Haq +2
Threads, a new microblogging platform from Meta, was launched in July 2023. In contrast to prior new platforms, Threads was borne out of an existing parent platform, Instagram, for…
Echo Chambers within the Russo-Ukrainian War: The Role of Bipartisan Users
Peixian Zhang, Ehsan-Ul Haq, Yiming Zhu +2
The ongoing Russia-Ukraine war has been extensively discussed on social media. One commonly observed problem in such discussions is the emergence of echo chambers, where users are…
Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks
Yiming Zhu, Peixian Zhang, Ehsan-Ul Haq +2
The release of ChatGPT has uncovered a range of possibilities whereby large language models (LLMs) can substitute human intelligence. In this paper, we seek to understand whether C…