An official website of the United States government
Podcasts have become daily companions for half a billion users. Given the enormous amount of podcast content available, highlights provide a valuable signal that helps viewers get the gist of an episode and decide if they want to invest in listening to it in its entirety. However, identifying highlights automatically is challenging due to the unstructured and long-form nature of the content. We introduce Rhapsody, a dataset of 13K podcast episodes paired with segment-level highlight scores derived from YouTube's 'most replayed' feature. We frame the podcast highlight detection as a segment-level binary classification task. We explore various baseline approaches, including zero-shot prompting of language models and lightweight finetuned language models using segment-level classification heads. Our experimental results indicate that even state-of-the-art language models like GPT-4o and Gemini struggle with this task, while models finetuned with in-domain data significantly outperform their zero-shot performance. The finetuned model benefits from leveraging both speech signal features and transcripts. These findings highlight the challenges for fine-grained information access in long-form spoken media.
more »
« less
This content will become publicly available on June 1, 2026
Leveraging generative AI for course learning outcome categorization using Bloom's taxonomy
Learning outcomes are clear and concise statements that describe what students should be able to do or know at the end of a particular course. These statements are crucial in instructional planning, curriculum development, and assessment of student progress and learning. Although there is no universal guidance on how to develop learning outcomes, Bloom’s taxonomy is one widely used framework that helps instructors develop outcomes that reflect different levels of thinking, from basic remembering to creative problem-solving. This study investigates the potential of generative AI, specifically GPT-4, in classifying course learning outcomes according to their respective cognitive levels within the revised Bloom’s taxonomy. To assess the effectiveness of GenAI, we conducted a comparative study using a dataset of 1000 annotated learning outcomes. We tested multiple prompt engineering strategies, including zero-shot, few-shot, chain-of-thought, rhetorical situation, and multiple binary questions, leveraging GPT-4. Classification performance was evaluated using accuracy, Cohen’s κ, and F1-score. The results indicate that the prompt incorporating rhetorical context and domain-specific knowledge achieved the highest classification performance, while the multiple binary question approach underperformed even compared to the zero-shot method. Furthermore, we compared the best-performing prompting strategy with a state-of-the-art classification model, BERT. Although the fine-tuned BERT model showed superior performance, prompt-based classification exhibited moderate to substantial agreement with expert annotations. Overall, this article demonstrates the potential of leveraging large language models to advance both theoretical understanding and practical application within the field of education and natural language processing.
more »
« less
- PAR ID:
- 10589953
- Publisher / Repository:
- Computers & Education: Artificial Intelligence
- Date Published:
- Journal Name:
- Computers and Education: Artificial Intelligence
- Volume:
- 8
- Issue:
- C
- ISSN:
- 2666-920X
- Page Range / eLocation ID:
- 100404
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Large language models such as GPT-3 (Brown et al., 2020) can perform arbitrary tasks without undergoing fine-tuning after being prompted with only a few labeled examples. An arbitrary task can be reformulated as a natural language prompt, and a language model can be asked to generate the completion, indirectly performing the task in a paradigm known as prompt-based learning. To date, emergent prompt-based learning capabilities have mainly been demonstrated for unidirectional language models. However, bidirectional language models pre-trained on denoising objectives such as masked language modeling produce stronger learned representations for transfer learning. This motivates the possibility of prompting bidirectional models, but their pre-training objectives have made them largely incompatible with the existing prompting paradigm. We present SAP (Sequential Autoregressive Prompting), a technique that enables the prompting of bidirectional models. Utilizing the machine translation task as a case study, we prompt the bidirectional mT5 model (Xue et al., 2021) with SAP and demonstrate its few-shot and zero-shot translations outperform the few-shot translations of unidirectional models like GPT-3 and XGLM (Lin et al., 2021), despite mT5's approximately 50% fewer parameters. We further show SAP is effective on question answering and summarization. For the first time, our results demonstrate prompt-based learning is an emergent property of a broader class of language models, rather than only unidirectional models.more » « less
-
Advances in large language models (LLMs) have empowered a variety of applications. However, there is still a significant gap in research when it comes to understanding and enhancing the capabilities of LLMs in the field of mental health. In this work, we present a comprehensive evaluation of multiple LLMs on various mental health prediction tasks via online text data, including Alpaca, Alpaca-LoRA, FLAN-T5, GPT-3.5, and GPT-4. We conduct a broad range of experiments, covering zero-shot prompting, few-shot prompting, and instruction fine-tuning. The results indicate a promising yet limited performance of LLMs with zero-shot and few-shot prompt designs for mental health tasks. More importantly, our experiments show that instruction finetuning can significantly boost the performance of LLMs for all tasks simultaneously. Our best-finetuned models, Mental-Alpaca and Mental-FLAN-T5, outperform the best prompt design of GPT-3.5 (25 and 15 times bigger) by 10.9% on balanced accuracy and the best of GPT-4 (250 and 150 times bigger) by 4.8%. They further perform on par with the state-of-the-art task-specific language model. We also conduct an exploratory case study on LLMs' capability on mental health reasoning tasks, illustrating the promising capability of certain models such as GPT-4. We summarize our findings into a set of action guidelines for potential methods to enhance LLMs' capability for mental health tasks. Meanwhile, we also emphasize the important limitations before achieving deployability in real-world mental health settings, such as known racial and gender bias. We highlight the important ethical risks accompanying this line of research.more » « less
-
Language model (LM) prompting—a popular paradigm for solving NLP tasks—has been shown to be susceptible to miscalibration and brittleness to slight prompt variations, caused by its discriminative prompting approach, i.e., predicting the label given the input. To address these issues, we propose Gen-Z—a generative prompting framework for zero-shot text classification. GEN-Z is generative, as it measures the LM likelihood of input text, conditioned on natural language descriptions of labels. The framework is multivariate, as label descriptions allow us to seamlessly integrate additional contextual information about the labels to improve task performance. On various standard classification benchmarks, with six open-source LM families, we show that zero-shot classification with simple contextualization of the data source of the evaluation set consistently outperforms both zero-shot and few-shot baselines while improving robustness to prompt variations. Further, our approach enables personalizing classification in a zero-shot manner by incorporating author, subject, or reader information in the label descriptions.more » « less
-
This study explores the potential of the large language model GPT-4 as an automated tool for qualitative data analysis by educational researchers, exploring which techniques are most successful for different types of constructs. Specifically, we assess three different prompt engineering strategies — Zero-shot, Few-shot, and Few-shot with contextual information — as well as the use of embeddings. We do so in the context of qualitatively coding three distinct educational datasets: Algebra I semi-personalized tutoring session transcripts, student observations in a game-based learning environment, and debugging behaviours in an introductory programming course. We evaluated the performance of each approach based on its inter-rater agreement with human coders and explored how different methods vary in effectiveness depending on a construct’s degree of clarity, concreteness, objectivity, granularity, and specificity. Our findings suggest that while GPT-4 can code a broad range of constructs, no single method consistently outperforms the others, and the selection of a particular method should be tailored to the specific properties of the construct and context being analyzed. We also found that GPT-4 has the most difficulty with the same constructs than human coders find more difficult to reach inter-rater reliability on.more » « less
