Sep 2026· The journal of classics teaching· 11 references
Abstract
Abstract This work focuses on an educational project for third-year students in Italian classical high schools, integrating generative artificial intelligence (AI) into the study of Latin. Using tools like ChatGPT, the project explores innovative methods to enhance linguistic and cultural understanding while promoting ethical AI use. Generative AI enables the study and learning of Latin language and culture through new solutions. This educational activity encourages critical thinking and dialogue on translational and linguistic choices, improving the ability to analyse Latin texts, formulate sentences in Latin, and better understand basic and everyday grammar. Creativity and active use of Latin are also emphasised. Collaborative and individual working methods facilitate the exploration of AI’s advantages and limitations, enriching traditional pedagogy with a modern, interactive approach. The project consists of five modules, each exploring how to integrate AI into the current teaching program for third-year students. Specifically, the modules aim to enhance students’ capabilities in analysing and translating Latin texts, highlighting differences between human-generated and AI-generated results. Students critically compare these methods, refining their grammatical and syntactical understanding. Collaboration and cooperation among students are also emphasised. For example, they use AI to create dialogues in Latin inspired by Plautus’s conversational style. The impact of the activity is assessed through an analysis of students’ translations, ethical reflections, and methodological insights. In this paper, we will share our experience with this experiment, which aims, with the help of technology, to present Latin as a dynamic and living language, underscoring the enduring relevance of the classical tradition in contemporary education.
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
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 paper presents a comprehensive overview of the Ultralytics YOLO family, emphasizing architectural evolution, benchmarking, deployment, and emerging directions from YOLOv5 through YOLO27, and examines detection, segmentation, depth, classification, pose, oriented detection, tracking, export, quantization, and deplo...
Empirically, PRISM reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines, and achieves this efficiency while simultaneously enhancing performance, surpassing models fine-tuned on the full dataset across eight multimodal and three language understanding benchmarks.
Jinhe Bi, Yifan Wang, Danqi Yan et al.· arXiv.org· 73 citations· ⚡4
This paper proposes adaptive sampling with approximate expected futures (ASAp), a decoding algorithm that guarantees the output to be grammatical while provably producing outputs that match the conditional probability of the LLM's distribution conditioned on the given grammar constraint.
Kanghee Park, Jiayu Wang, Taylor Berg-Kirkpatrick et al.· Neural Information Processin...· 70 citations· ⚡5
The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.
Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson· EUROMICRO Conference on Soft...· 64 citations· ⚡6
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduSep 30, 2026
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.