Jack Good

Ann-Kareen Gedeus, Jack Good, Nadine Wagener et al.

Embodied conversational agents (ECAs) need effective empathic grounding to foster social support and engagement. Expanding into emotional domains, ECAs now use Large Language Models (LLMs) and multimodal human-agent interactions to enhance their capabilities. Yet, understanding the impact of backchanneling modalities on young adults and their gender remains limited. We introduce TANDE, an LLM-powered ECA designed for emotional conversations with young adults, a population experiencing mental, personal, and social issues with limited tools to address them. In a within-subjects study with N=36 young adults, we explore nonverbal and combined verbal-and-nonverbal backchanneling modalities on rapport, empathy, and engagement and isolate for gender differences. Our research shows the importance of nuanced backchanneling cues with emotional ECAs with young adults, showing a preference for nonverbal cues. We derive design implications for more effective ECAs for emotional support and well-being in young adults. The code is available at https://github.com/Cornell-Tech-AIRLab/TANDE.

Jack Good, Jimit Majmudar, Christophe Dupuy et al. · amazon-science

Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learning of a model from a continual stream of data without keeping the entire history. In CL, the main challenge is \textit{forgetting} what was learned from past data. While replay-based algorithms that keep a small pool of past training data are effective to reduce forgetting, only simple replay sample selection strategies have been applied to CFL in prior work, and no previous work has explored coordination among clients for better sample selection. To bridge this gap, we adapt a replay sample selection objective based on loss gradient diversity to CFL and propose a new relaxation-based selection of samples to optimize the objective. Next, we propose a practical algorithm to coordinate gradient-based replay sample selection across clients without communicating private data. We benchmark our coordinated and uncoordinated replay sample selection algorithms against random sampling-based baselines with language models trained on a large scale de-identified real-world text dataset. We show that gradient-based sample selection methods both boost performance and reduce forgetting compared to random sampling methods, with our coordination method showing gains early in the low replay size regime (when the budget for storing past data is small).