Bot Generated Text
Bot-generated text, encompassing everything from social media posts to creative writing, is a rapidly evolving field focused on understanding, detecting, and controlling the output of automated text generation systems. Current research emphasizes improving the capabilities of these systems, particularly in areas like robotic control and nuanced human-computer interaction, while simultaneously developing robust detection methods using techniques like clustering, information theory, and large language models (LLMs). This research is crucial for addressing ethical concerns surrounding misinformation, malicious use of bots, and the broader societal impact of increasingly sophisticated AI-generated content.
Papers
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
Ethan A. Chi, Ashwin Paranjape, Abigail See, Caleb Chiam, Trenton Chang, Kathleen Kenealy, Swee Kiat Lim, Amelia Hardy, Chetanya Rastogi, Haojun Li, Alexander Iyabor, Yutong He, Hari Sowrirajan, Peng Qi, Kaushik Ram Sadagopan, Nguyet Minh Phu, Dilara Soylu, Jillian Tang, Avanika Narayan, Giovanni Campagna, Christopher D. Manning
Improving Bot Response Contradiction Detection via Utterance Rewriting
Di Jin, Sijia Liu, Yang Liu, Dilek Hakkani-Tur