The National Science Foundation (NSF) awarded a $270,000 EAGER (Early-Concept Grants for Exploratory Research) grant to the Massachusetts Institute of Technology (MIT) to develop an Artificial Intelligence (AI) or Large Language Model (LLM)-powered conversational tutoring system for Quantum Information Science and Engineering (QISE). The project, titled "TRUSTWORTHY AND ETHICAL AI TUTORS WITH FIRST-PRINCIPLES/AXIOMATIC REASONING", aims to create an interpretable AI tutor, called "AIR.QISE", that can provide deductive reasoning and explanations to students, rather than relying solely on information retrieval. The goal is to minimize the risk of "confidently wrong" responses (hallucination) often seen in standalone LLMs. The open-source system will leverage numerical tools and a domain-specific knowledge base to offer verifiable, first-principles-based responses to student queries in QISE. This EAGER program will support a proof-of-concept demonstration of the AIR.QISE technology within a conversational AI framework. The project period is from May 15, 2024, to October 31, 2025.
Generated 1/28/25, 8:32 AM