Radio remains a pervasive medium for mass information dissemination, with AM/FM stations reaching more Americans than either smartphone-based social networking or live television. Increasingly, radio broadcasts are also streamed online and accessed over the Internet. We present WavePulse, a framework that records, documents, and analyzes radio content in real-time. While our framework is generally applicable, we showcase the efficacy of WavePulse in a collaborative project with a team of political scientists focusing on the 2024 Presidential Elections. We use WavePulse to monitor livestreams of 396 news radio stations over a period of three months, processing close to 500,000 hours of audio streams. These streams were converted into time-stamped, diarized transcripts and analyzed to track answer key political science questions at both the national and state levels. Our analysis revealed how local issues interacted with national trends, providing insights into information flow. Our results demonstrate WavePulse's efficacy in capturing and analyzing content from radio livestreams sourced from the Web. Code and dataset can be accessed at \url{https://wave-pulse.io}.

Real-time flood forecasting plays a crucial role in enabling timely and effective emergency responses. However, a significant challenge lies in bridging the gap between complex numerical flood models and practical decision-making. Decision-makers often rely on experts to interpret these models for optimizing flood mitigation strategies. And the public requires complex techniques to inquiry and understand socio-cultural and institutional factors, often hinders the public's understanding of flood risks. To overcome these challenges, our study introduces an innovative solution: a customized AI Assistant powered by the GPT-4 Large Language Model. This AI Assistant is designed to facilitate effective communication between decision-makers, the general public, and flood forecasters, without the requirement of specialized knowledge. The new framework utilizes GPT-4's advanced natural language understanding and function calling capabilities to provide immediate flood alerts and respond to various flood-related inquiries. Our developed prototype integrates real-time flood warnings with flood maps and social vulnerability data. It also effectively translates complex flood zone information into actionable risk management advice. To assess its performance, we evaluated the prototype using six criteria within three main categories: relevance, error resilience, and understanding of context. Our research marks a significant step towards a more accessible and user-friendly approach in flood risk management. This study highlights the potential of advanced AI tools like GPT-4 in democratizing information and enhancing public engagement in critical social and environmental issues.

Large Language Model (LLM) assistants, such as ChatGPT, have emerged as potential alternatives to search methods for helping users navigate complex, feature-rich software. LLMs use vast training data from domain-specific texts, software manuals, and code repositories to mimic human-like interactions, offering tailored assistance, including step-by-step instructions. In this work, we investigated LLM-generated software guidance through a within-subject experiment with 16 participants and follow-up interviews. We compared a baseline LLM assistant with an LLM optimized for particular software contexts, SoftAIBot, which also offered guidelines for constructing appropriate prompts. We assessed task completion, perceived accuracy, relevance, and trust. Surprisingly, although SoftAIBot outperformed the baseline LLM, our results revealed no significant difference in LLM usage and user perceptions with or without prompt guidelines and the integration of domain context. Most users struggled to understand how the prompt's text related to the LLM's responses and often followed the LLM's suggestions verbatim, even if they were incorrect. This resulted in difficulties when using the LLM's advice for software tasks, leading to low task completion rates. Our detailed analysis also revealed that users remained unaware of inaccuracies in the LLM's responses, indicating a gap between their lack of software expertise and their ability to evaluate the LLM's assistance. With the growing push for designing domain-specific LLM assistants, we emphasize the importance of incorporating explainable, context-aware cues into LLMs to help users understand prompt-based interactions, identify biases, and maximize the utility of LLM assistants.

Chain-of-thought (CoT) prompting has been shown to empirically improve the accuracy of large language models (LLMs) on various question answering tasks. While understanding why CoT prompting is effective is crucial to ensuring that this phenomenon is a consequence of desired model behavior, little work has addressed this; nonetheless, such an understanding is a critical prerequisite for responsible model deployment. We address this question by leveraging gradient-based feature attribution methods which produce saliency scores that capture the influence of input tokens on model output. Specifically, we probe several open-source LLMs to investigate whether CoT prompting affects the relative importances they assign to particular input tokens. Our results indicate that while CoT prompting does not increase the magnitude of saliency scores attributed to semantically relevant tokens in the prompt compared to standard few-shot prompting, it increases the robustness of saliency scores to question perturbations and variations in model output.

Software configurations play a crucial role in determining the behavior of software systems. In order to ensure safe and error-free operation, it is necessary to identify the correct configuration, along with their valid bounds and rules, which are commonly referred to as software specifications. As software systems grow in complexity and scale, the number of configurations and associated specifications required to ensure the correct operation can become large and prohibitively difficult to manipulate manually. Due to the fast pace of software development, it is often the case that correct software specifications are not thoroughly checked or validated within the software itself. Rather, they are frequently discussed and documented in a variety of external sources, including software manuals, code comments, and online discussion forums. Therefore, it is hard for the system administrator to know the correct specifications of configurations due to the lack of clarity, organization, and a centralized unified source to look at. To address this challenge, we propose SpecSyn a framework that leverages a state-of-the-art large language model to automatically synthesize software specifications from natural language sources. Our approach formulates software specification synthesis as a sequence-to-sequence learning problem and investigates the extraction of specifications from large contextual texts. This is the first work that uses a large language model for end-to-end specification synthesis from natural language texts. Empirical results demonstrate that our system outperforms prior the state-of-the-art specification synthesis tool by 21% in terms of F1 score and can find specifications from single as well as multiple sentences.

NEW YORK, April 13 (Reuters) - Face it, we could all use a little help with our money. So who better to ask for personal finance advice than a couple of the most powerful chatbots on the planet? Both OpenAI's ChatGPT and Google's Bard are dominating headlines recently, for their generative capabilities and vast storehouses of information. Each has far more processing power than, say, any individual personal finance writer (ahem). What is one great business idea?

Efficient energy consumption is crucial for achieving sustainable energy goals in the era of climate change and grid modernization. Thus, it is vital to understand how energy is consumed at finer resolutions such as household in order to plan demand-response events or analyze impacts of weather, electricity prices, electric vehicles, solar, and occupancy schedules on energy consumption. However, availability and access to detailed energy-use data, which would enable detailed studies, has been rare. In this paper, we release a unique, large-scale, digital-twin of residential energy-use dataset for the residential sector across the contiguous United States covering millions of households. The data comprise of hourly energy use profiles for synthetic households, disaggregated into Thermostatically Controlled Loads (TCL) and appliance use. The underlying framework is constructed using a bottom-up approach. Diverse open-source surveys and first principles models are used for end-use modeling. Extensive validation of the synthetic dataset has been conducted through comparisons with reported energy-use data. We present a detailed, open, high resolution, residential energy-use dataset for the United States.

Many tasks in Natural Language Processing (NLP) and Computer Vision (CV) offer evidence that humans disagree, from objective tasks such as part-of-speech tagging to more subjective tasks such as classifying an image or deciding whether a proposition follows from certain premises. While most learning in artificial intelligence (AI) still relies on the assumption that a single (gold) interpretation exists for each item, a growing body of research aims to develop learning methods that do not rely on this assumption. In this survey, we review the evidence for disagreements on NLP and CV tasks, focusing on tasks for which substantial datasets containing this information have been created. We discuss the most popular approaches to training models from datasets containing multiple judgments potentially in disagreement. We systematically compare these different approaches by training them with each of the available datasets, considering several ways to evaluate the resulting models. Finally, we discuss the results in depth, focusing on four key research questions, and assess how the type of evaluation and the characteristics of a dataset determine the answers to these questions. Our results suggest, first of all, that even if we abandon the assumption of a gold standard, it is still essential to reach a consensus on how to evaluate models. This is because the relative performance of the various training methods is critically affected by the chosen form of evaluation. Secondly, we observed a strong dataset effect. With substantial datasets, providing many judgments by high-quality coders for each item, training directly with soft labels achieved better results than training from aggregated or even gold labels. This result holds for both hard and soft evaluation. But when the above conditions do not hold, leveraging both gold and soft labels generally achieved the best results in the hard evaluation. All datasets and models employed in this paper are freely available as supplementary materials.

When most people think of the connection between technology and jobs, they think of robots and automation taking over relatively unskilled jobs like factory work. And thus, the biggest toll from these technological advances would be on already hard-hit manufacturing regions of the Rust Belt. But a new wave of developments in artificial intelligence may have a greater effect on high-skilled jobs and high-tech knowledge regions. The study by Mark Muro, Jacob Whiton, and Robert Maxim takes a close look at the potential of artificial intelligence--or AI--to automate tasks that until now have required human intelligence and decision-making. As they put it: "Unlike robotics (associated with the factory floor) and computers (associated with routine office activities), AI has a distinctly white-collar bent."

Last November, Brookings published a report on artificial intelligence's impact on the workplace that immediately raised eyebrows. Many readers, journalists, and even experts were perplexed by the report's primary finding: that, for the most part, it is better-paid, better-educated white-collar workers who are most exposed to AI's potential economic disruption. This conclusion--by authors Mark Muro, Robert Maxim, and Jacob Whiton--seemed to fly in the face of the popular understanding of technology's future effects on workers. For years, we've been hearing about how these advancements will force mainly blue-collar, lower-income workers out of jobs, as robotics and technology slowly consume those industries. In an article about the November report, The Mercury News outlined this discrepancy: "The study released Wednesday by the Brookings Institution seems to contradict findings from previous studies--including Brookings' own--that showed lower-skilled workers will be most affected by robots and automation, which can involve AI."