Multimodal AI is an important step towards building effective tools to leverage multiple modalities in human-AI communication. Building a multimodal document-grounded AI system to interact with long documents remains a challenge. Our work aims to fill the research gap of directly leveraging grounded visuals from documents alongside textual content in documents for response generation. We present an interactive conversational AI agent 'MuDoC' based on GPT-4o to generate document-grounded responses with interleaved text and figures. MuDoC's intelligent textbook interface promotes trustworthiness and enables verification of system responses by allowing instant navigation to source text and figures in the documents. We also discuss qualitative observations based on MuDoC responses highlighting its strengths and limitations.

For example, in online learning, an AI social assistant may connect learners and thereby enhance social interaction. These social AI assistants too need to explain themselves in order to enhance transparency and trust with the learners. We present a method of self-explanation that uses introspection over a self-model of an AI social assistant. The self-model is captured as a functional model that specifies how the methods of the agent use knowledge to achieve its tasks. The process of generating self-explanations uses Chain of Thought to reflect on the self-model and ChatGPT to provide explanations about its functioning. We evaluate the self-explanation of the AI social assistant for completeness and correctness. We also report on its deployment in a live class.

Many hyper-personalized AI systems profile people's characteristics (e.g., personality traits) to provide personalized recommendations. These systems are increasingly used to facilitate interactions among people, such as providing teammate recommendations. Despite improved accuracy, such systems are not immune to errors when making inferences about people's most personal traits. These errors manifested as AI misrepresentations. However, the repercussions of such AI misrepresentations are unclear, especially on people's reactions and perceptions of the AI. We present two studies to examine how people react and perceive the AI after encountering personality misrepresentations in AI-facilitated team matching in a higher education context. Through semi-structured interviews (n=20) and a survey experiment (n=198), we pinpoint how people's existing and newly acquired AI knowledge could shape their perceptions and reactions of the AI after encountering AI misrepresentations. Specifically, we identified three rationales that people adopted through knowledge acquired from AI (mis)representations: AI works like a machine, human, and/or magic. These rationales are highly connected to people's reactions of over-trusting, rationalizing, and forgiving of AI misrepresentations. Finally, we found that people's existing AI knowledge, i.e., AI literacy, could moderate people's changes in their trust in AI after encountering AI misrepresentations, but not changes in people's social perceptions of AI. We discuss the role of people's AI knowledge when facing AI fallibility and implications for designing responsible mitigation and repair strategies.

Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on ChatGPT requires no prior training and uses a modular design to allow the integration of new APIs using a skill-based architecture inspired by XiaoIce. Jill Watson is also well-suited for intelligent textbooks as it can process and converse using multiple large documents. We exclusively utilize publicly available resources for reproducibility and extensibility. Comparative analysis shows that our system outperforms the legacy knowledge-based Jill Watson as well as the OpenAI Assistants service. We employ many safety measures that reduce instances of hallucinations and toxicity. The paper also includes real-world examples from a classroom setting that demonstrate different features of Jill Watson and its effectiveness.

From navigation systems to smart assistants, we communicate with various AI on a daily basis. At the core of such human-AI communication, we convey our understanding of the AI's capability to the AI through utterances with different complexities, and the AI conveys its understanding of our needs and goals to us through system outputs. However, this communication process is prone to failures for two reasons: the AI might have the wrong understanding of the user and the user might have the wrong understanding of the AI. To enhance mutual understanding in human-AI communication, we posit the Mutual Theory of Mind (MToM) framework, inspired by our basic human capability of "Theory of Mind." In this paper, we discuss the motivation of the MToM framework and its three key components that continuously shape the mutual understanding during three stages of human-AI communication. We then describe a case study inspired by the MToM framework to demonstrate the power of MToM framework to guide the design and understanding of human-AI communication.

Report on the 24th International Conference on Case-Based Reasoning Research and Development (ICCBR-2016)

The Twenty-Fourth International Conference on Case-Based Reasoning Research and Development, ICCBR 2016, was held October 31st to November 2nd, in Atlanta, Georgia, USA, colocated with the Fourth International Conference on Design and Creativity. ICCBR is the premier, annual meeting of the CBR community and the leading international conference on this topic. The theme for the ICCBR 2016 was Creativity. The conference chair was Ashok K. Goel, from Georgia Institute of Technology, USA, and the program cochairs were Belen Diaz-Agudo from Complutense University, Spain, and Thomas Roth-Berghofer from the University of West London, UK.

Using AI to Teach AI: Lessons from an Online AI Class

In fall 2014, we launched a foundational course in artificial intelligence (CS7637: Knowledge-Based AI) as part of the Georgia Institute of Technology's Online Master of Science in Computer Science program. We incorporated principles and practices from the cognitive and learning sciences into the development of the online AI course. We also integrated AI techniques into the instruction of the course, including embedding 100 highly focused intelligent tutoring agents in the video lessons. By now, more than 2000 students have taken the course. Evaluations have indicated that OMSCS students enjoy the course compared to traditional courses, and more importantly, that online students have matched residential students' performance on the same assessments. In this article, we present the design, delivery, and evaluation of the course, focusing on the use of AI for teaching AI. We also discuss lessons we learned for scaling the teaching and learning of AI.

During the last 36 years of its illustrious history, ince its inception in 1980, AI Magazine has played an the magazine has gone through several transformations. Now the magazine is going through another transition: David Leake, the longtime editor-in-chief is moving on after 17 years of distinguished service, though fortunately he will continue to advise us as editor emeritus. I am honored and delighted to follow David. I have been a member of the Editorial Board of AI Magazine for several years, associate editor since August 2015, and editor elect since February 2016; my tenure as editor-in-chief starts with this winter 2016 issue. I thank David, Managing Editor Mike Hamilton, former AAAI President Tom Dietterich, and AAAI for recruiting me for this challenge....