With the increasing integration of artificial intelligence (AI) technologies into educational settings, it becomes important to ensure responsible and effective use of these systems. This thesis addresses two critical challenges within AI-driven educational applications: the effortless integration of different Large Language Models (LLMs) and the mitigation of inappropriate content. An AI assistant chatbot was developed, allowing teachers to design custom chatbots and set rules for them, enhancing students’ learning experiences. Evaluation of LangChain as a framework for LLM integration, alongside various prompt engineering techniques including zero-shot, few-shot, zero-shot chain-of-thought, and prompt chaining, revealed LangChain’s suitability for this task and highlighted prompt chaining as the most effective method for mitigating inappropriate content in this use case. Looking ahead, future research could focus on further exploring prompt engineering capabilities and strategies to ensure uniform learning outcomes for all students, as well as leveraging LangChain to enhance the adaptability and accessibility of educational applications.

[pt] A tarefa chamada brevemente de Texto-para-SQL envolve a geração de uma consulta SQL com base em um banco de dados relacional e uma pergunta em linguagem natural. Embora os rankings de benchmarks conhecidos indiquem que Modelos de Linguagem Grandes (LLMs) se destacam nessa tarefa, eles são avaliados em bancos de dados com esquemas bastante simples. Esta dissertação investiga inicialmente o desempenho de modelos Texto-para-SQL baseados em LLMs em um banco de dados disponível ao público (Mondial)com um esquema conceitual complexo e um conjunto de 100 perguntas em Linguagem Natural (NL). Executando sob GPT-3.5 e GPT-4, os resultados deste primeiro experimento mostram que as ferramentas baseadas em LLM têm desempenho significativamente inferior ao relatado nesses benchmarks e enfrentam dificuldades com a vinculação de esquemas e joins, sugerindo que o esquema relacional pode não ser adequado para LLMs. Essa dissertação propõe então o uso de visões e descrições de dados amigáveis ao LLM para melhorara precisão na tarefa Texto-para-SQL. Em um segundo experimento, usando a estratégia com melhor performance, custo e benefício do experimento anterior e outro conjunto com 100 perguntas sobre um banco de dados do mundo real, os resultados mostram que a abordagem proposta é suficiente para melhorar consideravelmente a precisão da estratégia de prompt. Esse trabalho conclui com uma discussão dos resultados obtidos e sugere abordagens adicionais para simplificar a tarefa de Texto-para-SQL. / [en] The Text-to-SQL task involves generating an SQL query based on a given relational database and a Natural Language (NL) question. While the leaderboards of well-known benchmarks indicate that Large Language Models (LLMs) excel in this task, they are evaluated on databases with simpler schemas. This dissertation first investigates the performance of LLM-based Text-to-SQL models on a complex and openly available database (Mondial) with a large schema and a set of 100 NL questions. Running under GPT-3.5 and GPT-4, the results of this first experiment show that the performance of LLM-based tools is significantly less than that reported in the benchmarks and that these tools struggle with schema linking and joins, suggesting that the relational schema may not be suitable for LLMs. This dissertation then proposes using LLM-friendly views and data descriptions for better accuracy in the Text-to-SQL task. In a second experiment, using the strategy with better performance, cost and benefit from the previous experiment and another set with 100 questions over a real-world database, the results show that the proposed approach is sufficient to considerably improve the accuracy of the prompt strategy. This work concludes with a discussion of the results obtained and suggests further approaches to simplify the Text-to-SQL task.

Manuell granskning av användarrecensioner för att extrahera relevant informationkan vara en tidskrävande process. Denna rapport har undersökt om stora språkmodeller kan användas för att sammanfatta, extrahera och analysera nyckelinformation från recensioner, samt hur en sådan applikation kan konstrueras.  Det visade sig att olika modeller presterade olika bra beroende på mätvärden ochviktning mellan recall och precision. Vidare visade det sig att fine-tuning av språkmodeller som Llama 3 förbättrade prestationen vid klassifikation av användbara recensioner och ledde, enligt vissa mätvärden, till högre prestation än större språkmodeller som Chat-Bison. För engelskt översatta recensioner hade Llama 3:8b:Instruct, Chat-Bison samt den fine-tunade versionen av Llama 3:8b ett F4-makro-score på 0.89, 0.90 och 0.91 respektive. Ytterligare ett resultat är att de större modellerna Chat-Bison, Text-Bison och Gemini, presterade bättre i fallet för generering av sammanfattande texter, än de mindre modeller som testades vid inmatning av flertalet recensioner åt gången.  Generellt sett presterade språkmodellerna också bättre om recensioner först översattes till engelska innan bearbetning, snarare än då recensionerna var skrivna i originalspråk där de majoriteten av recensionerna var skrivna på svenska. En annan lärdom från förbearbetning av recensioner är att antal anrop till dessa språkmodeller kan minimeras genom att filtrera utifrån ordlängd och betyg.  Utöver språkmodeller visade resultaten att användningen av vektordatabaser och embeddings kan ge en större överblick över användbara recensioner genom vektordatabasers inbyggda förmåga att hitta semantiska likheter och samla liknande recensioner i kluster. / Manually reviewing user reviews to extract relevant information can be a time consuming process. This report investigates if large language models can be used to summarize, extract, and analyze key information from reviews, and how such anapplication can be constructed.  It was discovered that different models exhibit varying degrees of performance depending on the metrics and the weighting between recall and precision. Furthermore, fine-tuning of language models such as Llama 3 was found to improve performance in classifying useful reviews and, according to some metrics, led to higher performance than larger language models like Chat-bison. Specifically, for English translated reviews, Llama 3:8b:Instruct, Chat-bison, and Llama 3:8b fine-tuned had an F4 macro score 0.89, 0.90, 0.91 respectively. A further finding is that the larger models, Chat-Bison, Text-Bison, and Gemini performed better than the smaller models that was tested, when inputting multiple reviews at a time in the case of summary text generation.  In general, language models performed better if reviews were first translated into English before processing rather than when reviews were written in the original language where most reviews were written in Swedish. Additionally, another insight from the pre-processing phase, is that the number of API-calls to these language models can be minimized by filtering based on word length and rating. In addition to findings related to language models, the results also demonstrated that the use of vector databases and embeddings can provide a greater overview of reviews by leveraging the databases’ built-in ability to identify semantic similarities and cluster similar reviews together.