This study evaluates the performance of seven large language models (LLMs) in generating context-aware recommendations. The system is built on a collection of PDF documents (brochures) describing local events and activities, which are embedded into an FAISS vector store to support semantic retrieval. Synthetic user profiles are defined to simulate diverse preferences, while static weather conditions are incorporated to enhance the contextual relevance of recommendations. To further improve output quality, a reranking step, utilizing Cohere’s API, is used to refine the top retrieved results before passing them to the LLMs for final response generation. This allows better semantic organization of relevant content in line with user context. The main aim of this research is to identify which models best integrate multimodal inputs, such as user intent, profile attributes, environmental context and how these insights can inform the development of adaptive, personalized recommendation systems. The main contribution of this study is a structured comparative analysis of 7 LLMs, applied to a tourism-specific RAG framework, providing practical insights into how effectively different models integrate contextual factors to produce personalized recommendations. The evaluation revealed notable differences in model performance, with Qwen and Phi emerging as the strongest performers, whereas LLaMA frequently produced irrelevant recommendations. Moreover, many models favored gastronomy-related venues over other types of attractions. These findings indicate that although the RAG framework provides a solid foundation, the selection of underlying models plays an important role in achieving high quality recommendations.

This study presents SmirAI, an interface prototype for a Japanese-for-tourism language-learning application focusing on Croatian cultural heritage. The system combines virtual walks through selected locations with corpus-derived tourism discourse and learner-oriented dictionary entries based on authentic guided tour recordings. The paper reports the results of a user experience evaluation focusing on usability and perceived pedagogical usefulness. Intermediate-level learners expressed positive attitudes toward integrating authentic tourism content with structured vocabulary support. Developed within the VIRAI project, the study proposes a methodological model for Japanese for specific purposes and highlights the potential of corpus-informed digital walks for culturally situated language learning in Computer-Assisted Language Learning (CALL) and digital humanities.

This study evaluates the accuracy of medical-report interpretations generated by large language models in comparison to medically verified sources, with a particular focus on urology. The main goal is to examine the extent to which LLMs can reliably and precisely explain medical findings, with emphasis on expert urological terminology. For the evaluation of interpretation accuracy, real clinical documentation was used, specifically a dataset of 40 urological reports from the Clinical Hospital Center Rijeka. The generated explanations were compared with medically correct definitions using quantitative metrics assessing interpretability, specificity, and clinical accuracy. The results revealed a clear stratification of model performance, with DeepSeek-V3.2, GLM-4.6, MiMo-V2-Flash, and Qwen2.5-7B-Instruct achieving the highest semantic accuracy and consistency, while several models exhibited unstable behavior characterized by occasional catastrophic failures. Overall, the findings indicate that although LLMs can produce clinically coherent explanations of urological findings, their variability and susceptibility to hallucinations necessitate human oversight, supporting their use primarily as decision-support tools rather than autonomous clinical interpreters.

Large language models (LLMs) are increasingly integrated into educational settings, yet their pedagogical reliability remains insufficiently understood. Beyond overt hallucinations, which informed users readily recognize, a subtler failure mode consists of explanations that are coherent, authoritative, and pedagogically plausible while harbouring hidden conceptual flaws, responses we term Socratic traps. This paper introduces SocraticTrap-CS, a publicly available benchmark that probes the capacity of open-weight LLMs to generate such strategic misconceptions on demand. A single structured prompt explicitly elicited three outputs per concept (a correct explanation, an overt hallucination, and a strategic misconception), yielding 735 expert-annotated response segments from seven open-weight models across 35 core concepts in algorithms and data structures, programming languages and paradigms, databases, computer networks, and operating systems. Three domain experts independently annotated each segment using a three-class schema, achieving near-perfect agreement (Fleiss’ $\kappa =0.9487$). Because models were explicitly instructed to produce the misconception, the central metric quantifies adversarial instruction-following capacity rather than the base rate of such errors in naturalistic use and should be read as a conservative upper bound on model capability. Under these conditions, compliance reached 91.7% overall (100% for three models; 57.1% for the smallest model, Mistral 7B, whose lower rate plausibly reflects weaker instruction-following rather than greater safety). Expert-judged persuasiveness was moderate to high, errors were predominantly conceptual rather than factual, models differed significantly, and no statistically significant domain-level differences were detected. The benchmark reframes the evaluation of educational LLMs around pedagogical trustworthiness rather than factual correctness alone.