Iskanje po katalogu digitalne knjižnice

Opis: Manual assignment of Universal Decimal Classification (UDC) codes is time-consuming and inconsistent as digital library collections expand. This study evaluates 17 large language models (LLMs) as UDC classification recommender systems, including ChatGPT variants (GPT-3.5, GPT-4o, and o1-mini), Claude models (3-Haiku and 3.5-Haiku), Gemini series (1.0-Pro, 1.5-Flash, and 2.0-Flash), and Llama, Gemma, Mixtral, and DeepSeek architectures. Models were evaluated zero-shot on 900 English and Slovenian academic theses manually classified by professional librarians. Classification prompts utilized the RISEN framework, with evaluation using Levenshtein and Jaro–Winkler similarity, and a novel adjusted hierarchical similarity metric capturing UDC’s faceted structure. Proprietary systems consistently outperformed open-weight alternatives by 5–10% across metrics. GPT-4o achieved the highest hierarchical alignment, while open-weight models showed progressive improvements but remained behind commercial systems. Performance was comparable between languages, demonstrating robust multilingual capabilities. The results indicate that LLM-powered recommender systems can enhance library classification workflows. Future research incorporating fine-tuning and retrieval-augmented approaches may enable fully automated, high-precision UDC assignment systems.
Ključne besede: universal decimal classification, large language models, conversational systems, recommender systems, prompt engineering, zero-shot classification, hierarchical similarity
Objavljeno v DKUM: 21.07.2025; Ogledov: 0; Prenosov: 11
Celotno besedilo (447,50 KB)
Gradivo ima več datotek! Več...

Opis: This study investigates the effects of LLM-based coding assistance on web application development by students using a frontend framework. Rather than comparing different models, it focuses on how students interact with LLM tools to isolate the impact of query type on coding success. To this end, participants were instructed to rely exclusively on LLMs for writing code, based on a given set of specifications, and their queries were categorized into seven types: Error Fixing (EF), Feature Implementation (FI), Code Optimization (CO), Code Understanding (CU), Best Practices (BP), Documentation (DOC), and Concept Clarification (CC). The results reveal that students who queried LLMs for error fixing (EF) were statistically more likely to have runnable code, regardless of prior knowledge. Additionally, students seeking code understanding (CU) and error fixing performed better, even when normalizing for previous coding ability. These findings suggest that the nature of the queries made to LLMs influences the success of programming tasks and provides insights into how AI tools can assist learning in software development.
Ključne besede: large language models, LLMs, prompt engineering, query type analysis, AI-assisted programming, educational software development
Objavljeno v DKUM: 23.06.2025; Ogledov: 0; Prenosov: 8
Celotno besedilo (994,41 KB)
Gradivo ima več datotek! Več...

Opis: In the midst of industries being reshaped by the emergence of technologies our attention is drawn to the increasing trend of AI and its potential integration, in the work environment. At present, we recognise the swift evolution of technology and the necessity to align with current trends. In this thesis we delve into the world of content creation in tourism social media marketing. We specifically focus on how AI tools, like ChatGPT transform the way we generate content across social media platforms. Through the thesis we highlight the importance of content marketing in boosting brand visibility and engagement. We further explore how generative AI models can create content, enhance personalization and streamline marketing strategies. Additionally, we investigate the newly emerging field of prompt engineering, which focuses on improved interactions with generative AI models. While AI tools offer efficiency, we emphasize the need to strike a balance between automation and human driven creativity. In the evolving landscape of digital marketing, this study contributes insights into leveraging AI-powered content creation for enriching the tourism industry's social media endeavours.
Ključne besede: Content creation, artificial intelligence, ChatGPT, prompt engineering, social media marketing
Objavljeno v DKUM: 09.10.2023; Ogledov: 746; Prenosov: 132
Celotno besedilo (1,99 MB)