ChatGPT Generated Conversation
Research on ChatGPT-generated conversations explores how this large language model (LLM) performs in various interactive contexts, focusing on its capabilities, limitations, and potential biases. Current studies investigate its application in diverse fields, including education (e.g., essay scoring, literature review assistance), healthcare (e.g., medication management, robot interaction), and software development (e.g., code generation, library recommendation), often comparing its performance to human experts or other AI models. This work is significant because it helps assess the reliability and ethical implications of LLMs in real-world applications, informing the development of responsible AI and highlighting potential risks and benefits across numerous sectors.
Papers
Evaluating the Predictive Capacity of ChatGPT for Academic Peer Review Outcomes Across Multiple Platforms
Mike Thelwall, Abdullah Yaghi
How Good is ChatGPT at Audiovisual Deepfake Detection: A Comparative Study of ChatGPT, AI Models and Human Perception
Sahibzada Adil Shahzad, Ammarah Hashmi, Yan-Tsung Peng, Yu Tsao, Hsin-Min Wang
SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
Wanhua Li, Zibin Meng, Jiawei Zhou, Donglai Wei, Chuang Gan, Hanspeter Pfister
Is GPT-4 Less Politically Biased than GPT-3.5? A Renewed Investigation of ChatGPT's Political Biases
Erik Weber, Jérôme Rutinowski, Niklas Jost, Markus Pauly