Jan 2027· International journal of technology in education and science· 0 citations
EFL/ESL Teaching and Learning
Abstract
Generative artificial intelligence (AI) is increasingly used in English as a foreign language (EFL) writing for idea generation, planning, drafting, feedback, revision, and editing. However, its educational value depends not only on model capability but also on the quality of learners’ interactions with AI. This conceptually driven narrative review examines how prompt literacy has been conceptualized, its core dimensions, its role across the writing process, and its pedagogical and research implications. A transparent review procedure was used to synthesize 46 recent empirical studies and review papers published from 2023 to early 2025. The findings conceptualize prompt literacy as a multidimensional competence encompassing operational, strategic, evaluative, metacognitive, and ethical capacities. These capacities enable learners to define writing goals, obtain useful support, evaluate AI-generated outputs, preserve authorial voice, and integrate feedback responsibly. The review argues that prompt literacy should be treated as an explicit pedagogical objective rather than an incidental technical skill. It proposes an integrative framework linking learner conditions, prompt literacy dimensions, writing-process functions, and educational outcomes, while offering a clearer conceptual foundation and a practical agenda for instruction and future research in AI-assisted EFL writing.
This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.
F. Xia, Amir Zamir, Zhi-Yang He et al.· 2018 IEEE/CVF Conference on...· 1,069 citations· ⚡112
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.
This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...
Masoud Mohseni, Artur Scherer, K. Johnson et al.· arXiv.org· 121 citations· ⚡9
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.