Combining Cognitive and Generative AI for Self-explanation in Interactive AI Agents
This work addresses the need for explainable AI in educational tools like VERA, though it appears incremental by integrating existing AI techniques.
The study tackled the problem of generating self-explanations in interactive AI agents by combining cognitive AI (using a TMK model) and generative AI (using ChatGPT and LangChain) in the VERA learning environment, with a preliminary evaluation on 66 questions showing promising results.
The Virtual Experimental Research Assistant (VERA) is an inquiry-based learning environment that empowers a learner to build conceptual models of complex ecological systems and experiment with agent-based simulations of the models. This study investigates the convergence of cognitive AI and generative AI for self-explanation in interactive AI agents such as VERA. From a cognitive AI viewpoint, we endow VERA with a functional model of its own design, knowledge, and reasoning represented in the Task--Method--Knowledge (TMK) language. From the perspective of generative AI, we use ChatGPT, LangChain, and Chain-of-Thought to answer user questions based on the VERA TMK model. Thus, we combine cognitive and generative AI to generate explanations about how VERA works and produces its answers. The preliminary evaluation of the generation of explanations in VERA on a bank of 66 questions derived from earlier work appears promising.