Bai Zhen

Tanmay Sinha, Zhen Bai, Justine Cassell · cmu, eth-zurich

Curiosity is a vital metacognitive skill in educational contexts, leading to creativity, and a love of learning. And while many school systems increasingly undercut curiosity by teaching to the test, teachers are increasingly interested in how to evoke curiosity in their students to prepare them for a world in which lifelong learning and reskilling will be more and more important. One aspect of curiosity that has received little attention, however, is the role of peers in eliciting curiosity. We present what we believe to be the first theoretical framework that articulates an integrated socio-cognitive account of curiosity that ties observable behaviors in peers to underlying curiosity states. We make a bipartite distinction between individual and interpersonal functions that contribute to curiosity, and multimodal behaviors that fulfill these functions. We validate the proposed framework by leveraging a longitudinal latent variable modeling approach. Findings confirm a positive predictive relationship between the latent variables of individual and interpersonal functions and curiosity, with the interpersonal functions exercising a comparatively stronger influence. Prominent behavioral realizations of these functions are also discovered in a data-driven manner. We instantiate the proposed theoretical framework in a set of strategies and tactics that can be incorporated into learning technologies to indicate, evoke, and scaffold curiosity. This work is a step towards designing learning technologies that can recognize and evoke moment-by-moment curiosity during learning in social contexts and towards a more complete multimodal learning analytics. The underlying rationale is applicable more generally for developing computer support for other metacognitive and socio-emotional skills.

Zhen Bai, Frances Judd, Naomi Polinsky et al.

Children growing up in the era of Artificial Intelligence (AI) will be most impacted by the technology across their life span. Participatory Design (PD) is widely adopted by the Interaction Design and Children (IDC) community, which empowers children to bring their interests, needs, and creativity to the design process of future technologies. While PD has drawn increasing attention to human-centered AI design, it remains largely untapped in facilitating the design process of AI technologies relevant to children and their community. In this paper, we report intriguing children's design ideas on AI technologies resulting from the "Research and Design Challenge" of the 22nd ACM Interaction Design and Children (IDC 2023) conference. The diversity of design problems, AI applications and capabilities revealed by the children's design ideas shed light on the potential of engaging children in PD activities for future AI technologies. We discuss opportunities and challenges for accessible and inclusive PD experiences with children in shaping the future of AI-powered society.

Chen Qian, Dongrui Liu, Haochen Wen et al.

Large reasoning models (LRMs) have demonstrated impressive capabilities in complex problem-solving, yet their internal reasoning mechanisms remain poorly understood. In this paper, we investigate the reasoning trajectories of LRMs from an information-theoretic perspective. By tracking how mutual information (MI) between intermediate representations and the correct answer evolves during LRM reasoning, we observe an interesting MI peaks phenomenon: the MI at specific generative steps exhibits a sudden and significant increase during LRM's reasoning process. We theoretically analyze such phenomenon and show that as MI increases, the probability of model's prediction error decreases. Furthermore, these MI peaks often correspond to tokens expressing reflection or transition, such as ``Hmm'', ``Wait'' and ``Therefore,'' which we term as the thinking tokens. We then demonstrate that these thinking tokens are crucial for LRM's reasoning performance, while other tokens has minimal impacts. Building on these analyses, we propose two simple yet effective methods to improve LRM's reasoning performance, by delicately leveraging these thinking tokens. Overall, our work provides novel insights into the reasoning mechanisms of LRMs and offers practical ways to improve their reasoning capabilities. The code is available at https://github.com/ChnQ/MI-Peaks.