Globalization increasingly demands multilingual communication on the Internet, as well as in local communities. To create customized collaboration tools to support multilingual communities, the authors’ Language Grid, established ten years ago, has been improving Web-based services to communities throughout the world by providing highly adaptable infrastructure and access to a wide variety of language resources.

Phishing URL detection is critical due to the severe cybersecurity threats posed by phishing attacks. While traditional methods rely heavily on handcrafted features and supervised machine learning, recent advances in large language models (LLMs) provide promising alternatives. This paper presents a comprehensive benchmarking study of 21 state-of-the-art open-source LLMs—including Llama3, Gemma, Qwen, Phi, DeepSeek, and Mistral—for phishing URL detection. We evaluate four key prompt engineering techniques—zero-shot, role-playing, chain-of-thought, and few-shot prompting—using a balanced, publicly available phishing URL dataset, with no fine-tuning or additional training of the models conducted, reinforcing the zero-shot, prompt-based nature as a distinctive aspect of our study. The results demonstrate that large open-source LLMs (≥27B parameters) achieve performance exceeding 90% F1-score without fine-tuning, closely matching proprietary models. Among the prompt strategies, few-shot prompting consistently delivers the highest accuracy (91.24% F1 with Llama3.3_70b), whereas chain-of-thought significantly lowers accuracy and increases inference time. Additionally, our analysis highlights smaller models (7B–27B parameters) offering strong performance with substantially reduced computational costs. This study underscores the practical potential of open-source LLMs for phishing detection and provides insights for effective prompt engineering in cybersecurity applications.

We benchmark 22 open-source large language models (LLMs) against ChatGPT-4 and human annotators on two NLP tasks—sentiment analysis and emotion classification—for Indonesian tweets. This study contributes to NLP in a relatively low-resource language (Bahasa Indonesia) by evaluating zero-shot classification performance on a labeled tweet corpus. The dataset includes sentiment labels (Positive, Negative, Neutral) and emotion labels (Love, Happiness, Sadness, Anger, Fear).We compare model predictions to human annotations and report precision, recall, and F1-score, along with inference time analysis. ChatGPT-4 achieves the highest macro F1-score (0.84) on both tasks, slightly outperforming human annotators. The best-performing open-source models—such as LLaMA3.1_70B and Gemma2_27B—achieve over 90% of ChatGPT-4’s performance, while smaller models lag behind. Notably, some mid-sized models (e.g., Phi-4 at 14B parameters) perform comparably to much larger models on select categories. However, certain classes—particularly Neutral sentiment and Fear emotion—remain challenging, with lower agreement even among human annotators. Inference time varies significantly: optimized models complete predictions in under an hour, while some large models require several days. Our findings show that state-of-the-art open models can approach closed-source LLMs like ChatGPT-4 on Indonesian classification tasks, though efficiency and consistency in edge cases remain open challenges. Future work should explore fine-tuning multilingual LLMs on Indonesian data and practical deployment strategies in real-world applications.

This study explores the effects of interacting with AI vs. human interlocutors on English language learners’ speaking performance in a game-based learning context. We developed Taboo Talks, a word-guessing game in which learners alternated between giving and guessing clues with either an AI or a human partner. To evaluate the impact of interaction mode on oral proficiency, participants completed a story retelling task, assessed using complexity, accuracy, and fluency (CAF) metrics. Each participant engaged in both partner conditions, with group order counterbalanced. The results from the retelling task indicated modest improvements in fluency and complexity, particularly following interaction with the AI partner. Accuracy scores remained largely stable across conditions. Post-task reflections revealed that learners perceived AI partners as less intimidating, facilitating more relaxed language production, though concerns were noted regarding limited responsiveness. Qualitative analysis of the gameplay transcripts further revealed contrasting interactional patterns: AI partners elicited more structured interactions whereas human partners prompted more spontaneous and variable interactions. These findings suggest that AI-mediated gameplay can enhance specific dimensions of spoken language development and may serve as a complementary resource alongside human interaction.

In dynamic, open, and service-oriented computing environments, e.g., e-commerce and crowdsourcing, service consumers must choose one of the services or items to complete their tasks. Due to the scale and dynamic characteristics of these environments, service consumers may have little or no experience with the available services. To this end, reputation systems are proposed and have played a crucial role in the success of online service-oriented transactions. In this paper, we study the current reputation systems used in commercial environments. In these rating-based reputation systems, we found they are not only resilient to the changes (time lag) but also vulnerable to unfair ratings. To address the problems in parallel, we propose an adaptive reputation model (ARM). ARM can dynamically adjust its model parameters to adapt the latest changes in a service. To tackle time lag, the proposed model generalizes the fixed sliding window, used in current commercial platforms, into a dynamic sliding window mechanism. Thus, the model can completely mitigate the influence of obsolete ratings. To detect unfair ratings, our model implements a statistical strategy based on hypothesis testing after transforming the ratings in the linear window into residuals. Experiments not only validate the effectiveness of the proposed model but also show that it outperforms the existing reputation system by 45% on average based on five test cases. The results also show that the proposed model can asymptotically converge to the underlying reputation value as ratings begin to accumulate.

Japan's largest platform for academic e-journals: J-STAGE is a full text database for reviewed academic papers published by Japanese societies