Search
690 resources
-
António P. M. Gomes, Bruno F. Gonçalves,...|Dec 1st, 2024|conferencePaperAntónio P. M. Gomes, Bruno F. Gonçalves,...Dec 1st, 2024
This research aims to explore the potentialities and challenges of AI in education in Cape Verde, in order to understand how AI can be used in the teaching–learning context. To carry out the research, a qualitative methodology was adopted supported by a literature review. With support from the documents found, the benefits and potentialities were analyzed, reflecting on the ethical implications of the application of AI in education, with emphasis on privacy, data security and ethics. We...
-
Xinmeng Huang, Shuo Li, Mengxin Yu|Dec 1st, 2024|conferencePaperXinmeng Huang, Shuo Li, Mengxin YuDec 1st, 2024
-
Yang Jiang, Jiangang Hao, Michael Fauss,...|Aug 1st, 2024|journalArticleYang Jiang, Jiangang Hao, Michael Fauss,...Aug 1st, 2024
-
Yavuz Selim Kıyak|Apr 1st, 2024|journalArticleYavuz Selim KıyakApr 1st, 2024
-
Yavuz Selim Kıyak, Özlem Coşkun, Işıl İr...|May 1st, 2024|journalArticleYavuz Selim Kıyak, Özlem Coşkun, Işıl İr...May 1st, 2024
-
Matthias Carl Laupichler, Johanna Flora ...|May 1st, 2024|journalArticleMatthias Carl Laupichler, Johanna Flora ...May 1st, 2024
Abstract Problem Creating medical exam questions is time consuming, but well-written questions can be used for test-enhanced learning, which has been shown to have a positive effect on student learning. The automated generation of high-quality questions using large language models (LLMs), such as ChatGPT, would therefore be desirable. However, there are no current studies that compare students’ performance on LLM-generated questions to questions...
-
Yu Li, Shenyu Zhang, Rui Wu|Dec 1st, 2024|preprintYu Li, Shenyu Zhang, Rui WuDec 1st, 2024
Recent advancements in generative Large Language Models(LLMs) have been remarkable, however, the quality of the text generated by these models often reveals persistent issues. Evaluating the quality of text generated by these models, especially in open-ended text, has consistently presented a significant challenge. Addressing this, recent work has explored the possibility of using LLMs as evaluators. While using a single LLM as an evaluation agent shows potential, it is filled with...
-
Zhen Li, Xiaohan Xu, Tao Shen|Dec 1st, 2024|journalArticleZhen Li, Xiaohan Xu, Tao ShenDec 1st, 2024
In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This survey aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to...
-
Zhen Li, Xiaohan Xu, Tao Shen|Dec 1st, 2024|journalArticleZhen Li, Xiaohan Xu, Tao ShenDec 1st, 2024
In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This survey aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to...
-
Kacper Łodzikowski, Peter W. Foltz, John...|Dec 1st, 2024|journalArticleKacper Łodzikowski, Peter W. Foltz, John...Dec 1st, 2024
We discuss the implications of generative AI on education across four critical sections: the historical development of AI in education, its contemporary applications in learning, societal repercussions, and strategic recommendations for researchers. We propose ways in which generative AI can transform the educational landscape, primarily via its ability to conduct assessment of complex cognitive performances and create personalized content. We also address the challenges of effective...
-
Alan Mead, Chenxuan Zhou|Dec 1st, 2024|journalArticleAlan Mead, Chenxuan ZhouDec 1st, 2024
OpenAI’s GPT-3 model can write multiple-choice exam items. This paper reviewed the literature on automatic item generation and then described the recent history of OpenAI GPT models and their operation, and then described a methodology for generating items using these models. This study then critically evaluated GPT-3 at the task of writing multiple-choice exam items for a hypothetical psychometrics exam. We also compared two versions of the GPT-3 model (text-davinci-002 and...
-
Steven Moore, Eamon Costello, Huy A. Ngu...|Dec 1st, 2024|bookSectionSteven Moore, Eamon Costello, Huy A. Ngu...Dec 1st, 2024
-
Alexander Ngo, Saumya Gupta, Oliver Perr...|Jan 1st, 2024|journalArticleAlexander Ngo, Saumya Gupta, Oliver Perr...Jan 1st, 2024
-
Jon Saad-Falcon, Omar Khattab, Christoph...|Dec 1st, 2024|preprintJon Saad-Falcon, Omar Khattab, Christoph...Dec 1st, 2024
Evaluating retrieval-augmented generation (RAG) systems traditionally relies on hand annotations for input queries, passages to retrieve, and responses to generate. We introduce ARES, an Automated RAG Evaluation System, for evaluating RAG systems along the dimensions of context relevance, answer faithfulness, and answer relevance. By creating its own synthetic training data, ARES finetunes lightweight LM judges to assess the quality of individual RAG components. To mitigate potential...
-
The Chronicle of Higher Educ...|Dec 1st, 2024|reportThe Chronicle of Higher Educ...Dec 1st, 2024
-
Lijuan Wang, Miaomiao Zhao|Dec 1st, 2024|conferencePaperLijuan Wang, Miaomiao ZhaoDec 1st, 2024
-
Peiyi Wang, Lei Li, Zhihong Shao|Dec 1st, 2024|preprintPeiyi Wang, Lei Li, Zhihong ShaoDec 1st, 2024
In this paper, we present an innovative process-oriented math process reward model called \textbf{Math-Shepherd}, which assigns a reward score to each step of math problem solutions. The training of Math-Shepherd is achieved using automatically constructed process-wise supervision data, breaking the bottleneck of heavy reliance on manual annotation in existing work. We explore the effectiveness of Math-Shepherd in two scenarios: 1) \textit{Verification}: Math-Shepherd is utilized for...
-
Rose E. Wang, Qingyang Zhang, Carly Robi...|Dec 1st, 2024|preprintRose E. Wang, Qingyang Zhang, Carly Robi...Dec 1st, 2024
Scaling high-quality tutoring remains a major challenge in education. Due to growing demand, many platforms employ novice tutors who, unlike experienced educators, struggle to address student mistakes and thus fail to seize prime learning opportunities. Our work explores the potential of large language models (LLMs) to close the novice-expert knowledge gap in remediating math mistakes. We contribute Bridge, a method that uses cognitive task analysis to translate an expert's latent thought...
-
Ben Williamson|Mar 1st, 2024|journalArticleBen WilliamsonMar 1st, 2024
-
Joshua Wilson, Corey Palermo, Arianto Wi...|Jun 1st, 2024|journalArticleJoshua Wilson, Corey Palermo, Arianto Wi...Jun 1st, 2024