Sep 2026· Zenodo (CERN European Organization for Nuclear Research)
Abstract
This questionnaire was developed as an AI-mediated extension of the Revised Intercultural Communication Needs (RICN) Questionnaire developed by Ghorbani (2025). The instrument aims to examine learners' perceptions of ChatGPT as an intercultural mediator in English language learning contexts. The ChatGPT-Mediated Revised Intercultural Communication Needs (RICN) Questionnaire was developed to examine learners’ perceptions of ChatGPT as an intercultural mediator within English language learning and intercultural communication contexts. Building on the Revised Intercultural Communication Needs (RICN) framework, this instrument extends linguistic, affective/emotional, and cultural dimensions to generative artificial intelligence-mediated communication environments. The questionnaire consists of four dimensions: ChatGPT-Mediated Linguistic Needs, ChatGPT-Mediated Affective/ Emotional Needs, ChatGPT-Mediated Cultural Needs, and Perceived Role of ChatGPT as an Intercultural Mediator. The instrument includes 29 Likert-scale items designed for research applications in applied linguistics, second language acquisition, intercultural communication, and AI-assisted language learning.
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
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...
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
