Search for: All records

Abstract Worldwide, governments imposed non-pharmaceutical interventions (NPIs) during the COVID-19 pandemic to contain the pandemic more effectively. We examined the effectiveness of individual NPIs in the United States during the first wave of the pandemic. Three types of analyses were performed. First, a prototypical Bayesian hierarchical model was employed to gauge the effectiveness of five NPIs and they are gathering restriction, restaurant capacity restriction, business closure, school closure, and stay-at-home order in the 42 states with over 100 deaths by the end of the wave. Second, we examined the effectiveness of the face mask mandate, the sixth and most controversial NPI by counterfactual modeling, which is a variant of the prototypical Bayesian hierarchical model allowing us to answer the question of what if the state had imposed the mandate or not. The third analysis used an advanced Bayesian hierarchical model to evaluate the effectiveness of all six NPIs in all 50 states and the District of Columbia, and thereby provide a full-scale estimation of the effectiveness of NPIs and the relative effectiveness of each NPI in the entire United States. Our results have enhanced the collective knowledge on the general effectiveness of NPIs in arresting the spread of COVID-19. 

The paper explores the performance of LLMs in the context of multi-dimensional analytic writing assessments, i.e. their ability to provide both scores and comments based on multiple assessment criteria. Using a corpus of literature reviews written by L2 graduate students and assessed by human experts against 9 analytic criteria, we prompt several popular LLMs to perform the same task under various conditions. To evaluate the quality of feedback comments, we apply a novel feedback comment quality evaluation framework. This framework is interpretable, cost-efficient, scalable, and reproducible, compared to existing methods that rely on manual judgments. We find that LLMs can generate reasonably good and generally reliable multi-dimensional analytic assessments. We release our corpus and code\footnote{\url{https://github.com/jaaack-wang/multi-dimensional-analytic-writing-assessments}.} for reproducibility. 

This thesis investigates the computational modeling of belief and related cognitive states as expressed in text and speech. Understanding how speakers or authors convey commitment, certainty, and emotions is crucial for language understanding, yet poses significant challenges for current NLP systems. We present a comprehensive study spanning multiple facets of belief prediction. We begin by re-examining the widely used FactBank corpus, correcting a critical projection error and establishing new state-of-the-art results for author-only belief prediction through multi-task learning and error analysis. We then tackle the more complex task of source-and-target belief prediction, introducing a novel generative framework using Flan-T5. This includes developing a structured database representation for FactBank and proposing a linearized tree generation approach, culminating in the BeLeaf system for visualization and analysis, which achieves state-of-the-art performance on both FactBank and the MDP corpus. With the rise of large language models (LLMs), we investigate their zero-shot capabilities for the source-and-target belief task. We propose Unified and Hybrid prompting frameworks, finding that while current LLMs struggle, particularly with nested beliefs, our Hybrid approach paired with reasoning-focused LLMs achieves new state-of-the-art results on FactBank. Finally, we explore the role of multimodality among multiple cognitive states. We present the first study on multimodal belief prediction using the CB-Prosody corpus, demonstrating that integrating audio features via fine-tuned Whisper models significantly improves performance over text-only BERT models. We further introduce Synthetic Audio Data (SAD), showing that even synthetic audio generated by TTS systems provides orthogonal, beneficial signals for various cognitive state tasks (belief, emotion, sentiment). We conclude by presenting OmniVox, the first systematic evaluation of omni-LLMs for zero-shot emotion recognition directly from audio, demonstrating their competitiveness with fine-tuned models and analyzing their acoustic reasoning capabilities. 

The issue of fairness in decision-making is a critical one, especially given the variety of stakeholder demands for differing and mutually incompatible versions of fairness. Adopting a strategic interaction of perspectives provides an alternative to enforcing a singular standard of fairness. We present a web-based software application, FairPlay, that enables multiple stakeholders to debias datasets collaboratively. With FairPlay, users can negotiate and arrive at a mutually acceptable outcome without a universally agreed-upon theory of fairness. In the absence of such a tool, reaching a consensus would be highly challenging due to the lack of a systematic negotiation process and the inability to modify and observe changes. We have conducted user studies that demonstrate the success of FairPlay, as users could reach a consensus within about five rounds of gameplay, illustrating the application's potential for enhancing fairness in AI systems. 

We present a novel methodology for crafting effective public messages by combining large language models (LLMs) and conjoint analysis. Our approach personalizes messages for diverse personas – context-specific archetypes representing distinct attitudes and behaviors – while reducing the costs and time associated with traditional surveys. We tested this method in public health contexts (e.g., COVID-19 mandates) and civic engagement initiatives (e.g., voting). A total of 153 distinct messages were generated, each composed of components with varying levels, and evaluated across five personas tailored to each context. Conjoint analysis identified the most effective message components for each persona, validated through a study with 2,040 human participants. This research highlights LLMs’ potential to enhance public communication, providing a scalable, cost-effective alternative to surveys, and offers new directions for HCI, particularly for the design of adaptive, user-centered, persona-driven interfaces and systems. 

When reading narratives, human readers rely on their Theory of Mind (ToM) to infer not only what the characters know from their utterances, but also whether characters are likely to share common ground. As in human conversation, such decisions are not infallible but probabilistic, based on the evidence available in the narrative. By responding on a scale (rather than Yes/No), humans can indicate commitment to their inferences about what characters know (ToM). We use two prompting approaches to explore (i) how well LLM judgments align with human judgments, and (ii) how well LLMs infer the author’s intent from utterances intended to project knowledge in narratives. 

High Voltage Direct Current (HVDC) technology is a cornerstone of efficient Offshore Wind Farm (OWF) power transmission. This review examines the integration of HVDC technology in OWFs, considering collection and transmission aspects. The analysis is structured around four key dimensions: economic considerations, connection topologies, converter designs, and technical modeling. It begins with an in-depth economic analysis, evaluating cost-effectiveness, reliability, and market dynamics, focusing on investment, operational costs, and lifecycle expenses. Building on this foundation, the review explores various collection and transmission architectures, highlighting their technical and economical trade-offs, and evaluates power converter designs for efficiency, reliability, and offshore adaptability. Finally, advanced modeling and simulation techniques are reviewed to optimize system performance, enhance reliability, and balance computational efficiency. Throughout each of the four sections, economic and technical constraints are considered together. This helps to improve understanding of how systems can be designed in a way that meets the constraints of both fields and to enhance feasibility on both dimensions. These insights provide a holistic framework for sustainable and economically viable Offshore Wind Energy (OWE) integration.