Research Papers

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Can AI Fact-Check Itself? Multi-Agent Debates Hold the Key

Xiaoxi Sun|Jinpeng Li|Yan Zhong|Dongyan Zhao|Rui Yan

ChatGPT’s Dark Side: How It Could Help Crypto Scammers

Wail Zellagui|Abdessamad Imine|Yamina Tadjeddine

Can AI Conquer Cross-Domain Recommendations?

Tingjia Shen|Hao Wang|Jiaqing Zhang|Sirui Zhao|Liangyue Li|Zulong Chen|Defu Lian|Enhong Chen

Unlocking AI’s Long-Term Memory: How LLMs Can Finally Read Whole Books

Xihang Yue|Linchao Zhu|Yi Yang

The AI Debater: New Dataset Fuels Argument Summarization Research

Hao Li|Yuping Wu|Viktor Schlegel|Riza Batista-Navarro|Tharindu Madusanka|Iqra Zahid|Jiayan Zeng|Xiaochi Wang|Xinran He|Yizhi Li|Goran Nenadic

Can AI Know When It’s Clueless? A New Way to Measure AI Certainty

Shuang Ao|Stefan Rueger|Advaith Siddharthan

The Truth About Misinformation: Why Citing Science Doesn't Mean It's True

Max Glockner|Yufang Hou|Preslav Nakov|Iryna Gurevych

Can LLMs Really Reason? Putting Llama 2 to the Math Test

Flavio Petruzzellis|Alberto Testolin|Alessandro Sperduti

Can AI Fix Your Grammar? A New Dataset for Perfecting Automated Proofreading

Jeiyoon Park|Chanjun Park|Heuiseok Lim

The first platform built for prompt engineering