161 resources

  • Abhimanyu Dubey, Abhinav Jauhri, Abhinav...
    |
    Aug 15th, 2024
    |
    preprint
    Abhimanyu Dubey, Abhinav Jauhri, Abhinav...
    Aug 15th, 2024

    Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language...

  • Hua Shen, Tiffany Knearem, Reshmi Ghosh,...
    |
    Aug 10th, 2024
    |
    preprint
    Hua Shen, Tiffany Knearem, Reshmi Ghosh,...
    Aug 10th, 2024

    Recent advancements in general-purpose AI have highlighted the importance of guiding AI systems towards the intended goals, ethical principles, and values of individuals and groups, a concept broadly recognized as alignment. However, the lack of clarified definitions and scopes of human-AI alignment poses a significant obstacle, hampering collaborative efforts across research domains to achieve this alignment. In particular, ML- and philosophy-oriented alignment research often views AI...

  • Aug 7th, 2024
    |
    webpage
    Aug 7th, 2024
  • Hinako Akeyama, Alan T Yang, Amirhessam ...
    |
    Aug 1st, 2024
    |
    conferencePaper
    Hinako Akeyama, Alan T Yang, Amirhessam ...
    Aug 1st, 2024

    This paper explores the role of Artificial Intelligence in education (AIEd) with an emphasis on the use of chatbots to promote students’ learning outcomes and grit characteristics. This paper proposes a framework derived from the deliberate practice and technology acceptance model (TAM). Understanding the importance of teachers’ perspectives and support of students, this framework presents a means to empower students’ learning in a non-threatening yet productive manner while captivating the...

  • Liu
    |
    Aug 1st, 2024
    |
    conferencePaper
    Liu
    Aug 1st, 2024
  • Jul 30th, 2024
    |
    blogPost
    Jul 30th, 2024
  • Hotaka Maeda
    |
    Jul 29th, 2024
    |
    preprint
    Hotaka Maeda
    Jul 29th, 2024

    Abstract Field-testing is a necessary but resource-intensive step in the development of high-quality educational assessments. I present an innovative method for field-testing newly written exam items by replacing human examinees with artificially intelligent (AI) examinees. The proposed approach is demonstrated using 466 four-option multiple-choice English grammar questions. Pre-trained transformer language models are fine-tuned based on the 2-parameter logistic (2PL)...

  • S Christie, Baptiste Moreau-Pernet, Yu T...
    |
    Jul 24th, 2024
    |
    conferencePaper
    S Christie, Baptiste Moreau-Pernet, Yu T...
    Jul 24th, 2024

    Large language models (LLMs) are increasingly being deployed in user-facing applications in educational settings. Deployed applications often augment LLMs with fine-tuning, custom system prompts, and moderation layers to achieve particular goals. However, the behaviors of LLM-powered systems are difficult to guarantee, and most existing evaluations focus instead on the performance of unmodified 'foun-dation' models. Tools for evaluating such deployed systems are currently sparse, inflexible,...

  • Steve Lohr
    |
    Jul 23rd, 2024
    |
    newspaperArticle
    Steve Lohr
    Jul 23rd, 2024

    A.I.’s math problem reflects how much the new technology is a break with computing’s past.

  • Nigel Fernandez, Alexander Scarlatos, An...
    |
    Jul 22nd, 2024
    |
    preprint
    Nigel Fernandez, Alexander Scarlatos, An...
    Jul 22nd, 2024

    Automated teaching assistants and chatbots have significant potential to reduce the workload of human instructors, especially for logistics-related question answering, which is important to students yet repetitive for instructors. However, due to privacy concerns, there is a lack of publicly available datasets. We introduce SyllabusQA, an open-source dataset with 63 real course syllabi covering 36 majors, containing 5,078 open-ended course logistics-related question-answer pairs that are...

  • Joy He-Yueya, Wanjing Anya Ma, Kanishk G...
    |
    Jul 22nd, 2024
    |
    preprint
    Joy He-Yueya, Wanjing Anya Ma, Kanishk G...
    Jul 22nd, 2024

    Language models (LMs) are increasingly used to simulate human-like responses in scenarios where accurately mimicking a population's behavior can guide decision-making, such as in developing educational materials and designing public policies. The objective of these simulations is for LMs to capture the variations in human responses, rather than merely providing the expected correct answers. Prior work has shown that LMs often generate unrealistically accurate responses, but there are no...

  • Wesley Morris, Langdon Holmes, Joon Suh ...
    |
    Jul 18th, 2024
    |
    journalArticle
    Wesley Morris, Langdon Holmes, Joon Suh ...
    Jul 18th, 2024

    Recent developments in the field of artificial intelligence allow for improved performance in the automated assessment of extended response items in mathematics, potentially allowing for the scoring of these items cheaply and at scale. This study details the grand prize-winning approach to developing large language models (LLMs) to automatically score the ten items in the National Assessment of Educational Progress (NAEP) Math Scoring Challenge. The approach uses extensive preprocessing that...

  • Sami Baral, Eamon Worden, Wen-Chiang Lim...
    |
    Jul 12th, 2024
    |
    journalArticle
    Sami Baral, Eamon Worden, Wen-Chiang Lim...
    Jul 12th, 2024

    The effectiveness of feedback in enhancing learning outcomes is well documented within Educational Data Mining (EDM). Various prior research have explored methodologies to enhance the effectiveness of feedback to students in various ways. Recent developments in Large Language Models (LLMs) have extended their utility in enhancing automated feedback systems. This study aims to explore the potential of LLMs in facilitating automated feedback in math education in the form of numeric assessment...

  • Xinyi Lu, Xu Wang
    |
    Jul 9th, 2024
    |
    conferencePaper
    Xinyi Lu, Xu Wang
    Jul 9th, 2024

    Evaluating the quality of automatically generated question items has been a long standing challenge. In this paper, we leverage LLMs to simulate student profiles and generate responses to multiple-choice questions (MCQs). The generative students' responses to MCQs can further support question item evaluation. We propose Generative Students, a prompt architecture designed based on the KLI framework. A generative student profile is a function of the list of knowledge components the student has...

  • Pepper Miller, Kristen DiCerbo
    |
    Jul 3rd, 2024
    |
    preprint
    Pepper Miller, Kristen DiCerbo
    Jul 3rd, 2024

    Large Language Models (LLMs) face documented challenges in solving mathematical problems. While substantial work has been done to quantify and improve LLMs’ abilities to solve static math problems, evaluating their performance in real-time math tutoring scenarios presents distinct challenges that remain underexplored. This paper specifically addresses the accuracy of LLMs in performing math correctly while tutoring students. It highlights the unique difficulties of this context, classifies...

  • Christopher Michael Ormerod, Alexander K...
    |
    Jul 2nd, 2024
    |
    preprint
    Christopher Michael Ormerod, Alexander K...
    Jul 2nd, 2024

    Current research on generative language models (GLMs) for automated text scoring (ATS) has focused almost exclusively on querying proprietary models via Application Programming Interfaces (APIs). Yet such practices raise issues around transparency and security, and these methods offer little in the way of efficiency or customizability. With the recent proliferation of smaller, open-source models, there is the option to explore GLMs with computers equipped with modest, consumer-grade...

  • Kai Guo
    |
    Jul 1st, 2024
    |
    journalArticle
    Kai Guo
    Jul 1st, 2024

    Peer feedback plays an important role in promoting learning in the writing classroom. However, providing high-quality feedback can be demanding for student reviewers. To address this challenge, this article proposes an AI-enhanced approach to peer feedback provision. I introduce EvaluMate, a newly developed online peer review system that leverages ChatGPT, a large language model (LLM), to scaffold student reviewers’ feedback generation. I discuss the design and functionality of EvaluMate,...

  • Xiaoyi Tang, Hongwei Chen, Daoyu Lin
    |
    Jul 1st, 2024
    |
    journalArticle
    Xiaoyi Tang, Hongwei Chen, Daoyu Lin
    Jul 1st, 2024
  • Okan Bulut, Maggie Beiting-Parrish, Jodi...
    |
    Jun 27th, 2024
    |
    preprint
    Okan Bulut, Maggie Beiting-Parrish, Jodi...
    Jun 27th, 2024

    The integration of artificial intelligence (AI) in educational measurement has revolutionized assessment methods, enabling automated scoring, rapid content analysis, and personalized feedback through machine learning and natural language processing. These advancements provide timely, consistent feedback and valuable insights into student performance, thereby enhancing the assessment experience. However, the deployment of AI in education also raises significant ethical concerns regarding...

  • Jooyoung Lee, Toshini Agrawal, Adaku Uch...
    |
    Jun 24th, 2024
    |
    preprint
    Jooyoung Lee, Toshini Agrawal, Adaku Uch...
    Jun 24th, 2024

    Recent literature has highlighted potential risks to academic integrity associated with large language models (LLMs), as they can memorize parts of training instances and reproduce them in the generated texts without proper attribution. In addition, given their capabilities in generating high-quality texts, plagiarists can exploit LLMs to generate realistic paraphrases or summaries indistinguishable from original work. In response to possible malicious use of LLMs in plagiarism, we introduce...

Last update from database: 01/12/2025, 16:15 (UTC)
Powered by Zotero and Kerko.