Team: UIUC (Lead), Northeastern University, USC
Description: Conversational agents have reached remarkable advancements with the advent of large language models (LLMs). Despite their impressive capabilities, these models frequently suffer from the issue of hallucinations, where they generate information that is incorrect or not grounded in reality. Moreover, users often tend to over-rely on LLM-based AI agents, accepting the AI’s suggestions even when they are erroneous. In the context of task-oriented conversations, such overreliance can lead to incorrect or incomplete task execution, thereby undermining the system’s reliability. This project explores building an accountability modeling to prevent overreliance on task-oriented conversational AI. You can find more information on the Project BECAREFUL Website.
Team: Univ. at Buffalo (Lead), UIUC, UCLA, and others
Description: The Center for Early Literacy and Responsible AI (CELaRAI), funded by the Institute of Education Sciences (IES), leads groundbreaking research on the integration of generative artificial intelligence (AI) in early literacy education. Focused on transforming K–2 beginning reading materials, CELaRAI is developing the innovative AI Reading Enhancer (AIRE), a student-focused tool designed to personalize text generation, provide real-time reading analysis, and offer on-the-spot literacy support. By advancing skills like phonics, word recognition, fluency, and comprehension, particularly for children from culturally and linguistically diverse backgrounds, CELaRAI is setting new benchmarks in literacy education. The center also serves as a national thought leader on responsible AI use, fostering impactful research, outreach, and capacity-building initiatives to shape the future of early literacy. You can find more information on the CELaRAI project pages.
Team: UIUC
Description: This research project, funded by the Microsoft Accelerating Foundation Models Research: Benchmarks, Evaluation and Measurement program focuses on assessing the task completion abilities of large language models (LLMs) through multi-turn conversational interactions within a multi-agent framework.
We are part of the Siebel School of Computing and Data Science at the University of Illinois Urbana-Champaign.
© 2024 ConvAI Lab @ UIUC. Site built with Jekyll; forked from here.
