Sep 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
This preprint addresses a fundamental, unresolved question in modern educational technology: the contrast between the enthusiastic anticipation of LLMs' potential benefits and the thorough scrutiny of the dangers posed by AI-created "hallucinations." The author argues that AI failures in instructional settings are not merely software bugs, but a linguo-pragmatic issue. When users interact with a probabilistic machine using casual, ambiguous natural language, the AI's algorithm dilutes the semantic focus, leading to logical errors. However, within academic problem-solving, natural language transforms into a rigorous, professional sub-language that demands strict structural control. This work is highly relevant for teachers, educational technologists, applied linguists, and curriculum designers looking for a structured, pedagogically secure, and cost-free methodology to safely integrate Generative AI into their disciplines. Fields: Artificial Intelligence in Education, Applied Linguistics, Cognitive Science, Linguistic Pragmatics, Instructional Design.
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 of such models.
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.
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
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
The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.
Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al.· arXiv.org· 62 citations· ⚡3
This paper designs Markov decision processes (MDPs) for different combinatorial problems and proposes to train conditional GFlowNets to sample from the solution space and demonstrates that GFlowNet policies can efficiently find high-quality solutions.
Dinghuai Zhang, H. Dai, Esmeralda S. Whitammer et al.· Advances in Neural Informati...· 59 citations· ⚡8
The professor of physics and inaugural director of the NSF AI Institute for Artificial Intelligence and Fundamental Interactions will lead LNS and continue his research in particle physics.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
