Assessing short answers in educational settings is challenging due to the need for scalability and accuracy, which led to the field of Automatic Short Answer Grading (ASAG). Traditional machine learning models, such as ensemble and embeddings, have been widely researched in ASAG, but they often suffer from generalizability issues. Recently, Large Language Models (LLMs) emerged as an alternative to optimize ASAG systems. However, previous research has failed to present a comprehensive analysis of LLMs' performance powered by prompt engineering strategies and compare its capabilities to traditional models. This study presents a comparative analysis between traditional machine learning models and GPT-4 in the context of ASAG. We investigated the effectiveness of different models and text representation techniques and explored prompt engineering strategies for LLMs. The results indicate that traditional machine learning models outperform LLMs. However, GPT-4 showed promising capabilities, especially when configured with optimized prompt components, such as few-shot examples and clear instructions. This study contributes to the literature by providing a detailed evaluation of LLM performance compared to traditional machine learning models in a multilingual ASAG context, offering insights for developing more efficient automatic grading systems.

Question-answering systems facilitate adaptive learning and respond to student queries, making education more responsive. Despite that, challenges such as natural language understanding and context management complicate their widespread adoption, where Large Language Models (LLMs) offer a promising solution. However, existing research is predominantly focused on English, proprietary models, and often limited to a single question type, subject, or skill, leaving a gap in understanding LLMs' performance in languages like Brazilian Portuguese and across questions of various characteristics. This study investigates how LLMs could be integrated in an educational question-answering system efficiently to answer different question types (multiple-choice, cloze, open-ended), subjects (mathematics and Portuguese language), and skills (summation/subtraction, multiplication, interpretation, and grammar), evaluating answers by GPT-4 - the main LLM at the time of writing - and Sabiá - the open-source Brazilian Portuguese LLM - based on grades assigned by two experienced teachers. Overall, both LLMs demonstrated strong overall performance, with mean scores close to 9.8 out of 10. However, specific challenges emerged, with distinct strengths and weaknesses observed for each model, such as GPT-4's error in a multiple-choice subtraction question and Sabiá's misinterpretation of a cloze question.

Artificial Intelligence Planning (AIP) is a technique that can be used to customize and automate one or more stages of the teaching process, in order to provide customized pedagogical recommendations. In order to investigate the advances, challenges and limitations of this technique in this scenario, this paper presents a Systematic Review of Literature (SRL), whose results allowed to observe that the recommendation of personalized learning paths are the main pedagogical actions addressed. In this regard, we also note that it is important to advance the research in this area, proposing a better refinement in the modeling of the learner, besides expanding the universe of recommended pedagogical actions.