Lugares de Memória Digitais: um Sistema Tutor Inteligente Baseado em RAG para a Preservação da História de Pelotas
Resumo
Este artigo apresenta um sistema tutor inteligente de baixo custo baseado em Retrieval-Augmented Generation para o ensino e a preservação da memória histórica e cultural de um município do Rio Grande do Sul, cujo conhecimento local corre risco de dissipação. O corpus de recuperação é composto por obras de referência sobre a história local. A avaliação abrangeu a qualidade da geração, por um especialista de domínio e por LLM as a Judge, e a qualidade da recuperação, pela análise dos trechos top-k e por um teste de verificação factual com informações incorretas. Conjuntamente, tais métodos evidenciam o potencial da referida abordagem para a mediação tecnológica da memória coletiva em contextos educacionais e culturais.
Palavras-chave:
Retrieval-Augmented Generation, Sistema Tutor Inteligente, Memória Cultural
Referências
Akgun, S. and Greenhow, C. (2022). Artificial intelligence in education: Addressing ethical challenges in k-12 settings. AI and Ethics, 2(3):431–440.
Alario-Hoyos, C., Kemcha, R., Kloos, C. D., Callejo, P., Estévez-Ayres, I., Santín-Cristóbal, D., Cruz-Argudo, F., and López-Sánchez, J. L. (2024). Tailoring your code companion: Leveraging llms and rag to develop a chatbot to support students in a programming course. In 2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE), pages 1–8. IEEE.
Anderson, J. R., Boyle, C. F., and Reiser, B. J. (1985). Intelligent tutoring systems. Science, 228(4698):456–462.
Anthropic (2026). Claude 4.7 opus. Software / LLM. Versão 4.7.
Bhatia, G., Peyrard, M., and Zhao, W. (2025). Date fragments: A hidden bottleneck of tokenization for temporal reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 3201–3219.
Chroma (2022). Chroma: the ai-native open-source embedding database. [link]. Acesso em: Março de 2026.
da Costa, V. K., Zen, E., da Silva, A. B. A., and Tavares, T. A. (2023). Experiências com uso de mesa tangível em espaços de educação não formal. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 983–994. SBC.
Danuarta, L., Mawardi, V. C., and Lee, V. (2024). Retrieval-augmented generation (rag) large language model for educational chatbot. In 2024 Ninth International Conference on Informatics and Computing (ICIC), pages 1–6. IEEE.
de Sousa, R. R. A., Santos, A., and Diogo, A. Q. (2023). A preservação da memória histórica na era digital: Desafios, oportunidades e tecnologias interativas no ensino e na pesquisa. Revista Inter-Ação.
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), pages 4171–4186.
Halbwachs, M. (1997). La mémoire collective. Albin Michel.
Idris, M. Z., Mustaffa, N. B., and Yusoff, S. O. S. (2016). Preservation of intangible cultural heritage using advance digital technology: Issues and challenges. Harmonia: Journal of Arts Research and Education, 16(1):1–13.
Isotani, S., Bittencourt, I. I., Challco, G. C., Dermeval, D., and Mello, R. F. (2023). Aied unplugged: Leapfrogging the digital divide to reach the underserved. In International Conference on Artificial Intelligence in Education, pages 772–779. Springer.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–9474.
Liu, Z., Agrawal, P., Singhal, S., Madaan, V., Kumar, M., and Verma, P. K. (2025). Lpi-tutor: an llm based personalized intelligent tutoring system using rag and prompt engineering. PeerJ Computer Science, 11:e2991.
Mello, R. F., Anthony, L., Lobo, J., Ribeiro, F. G. C., Xavier, C., da Costa, N. T., Gasevic, D., and Rodrigues, L. (2025). Empowering equitable learning with llms: enhancing writing skills in low-resource contexts. In European Conference on Technology Enhanced Learning, pages 183–197. Springer.
Microsoft (2024). Markitdown: Python tool for converting various files to markdown. [link].
Nora, P. and Erll, A. (1997). Les lieux de mémoire, volume 3. Gallimard Paris.
Ollama (2023). Ollama. [link]. Acesso em: Março de 2026.
Streamlit (2019). Streamlit: A faster way to build and share data apps. [link]. Acesso em: Março de 2026.
Team, G., Kamath, A., Ferret, J., Pathak, S., Vieillard, N., et al. (2025). Gemma 3 technical report. arXiv.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
Wang, S., Xu, T., Li, H., Zhang, C., Liang, J., Tang, J., Yu, P. S., and Wen, Q. (2026). Large language models for education: A survey and outlook. IEEE Signal Processing Magazine, 42(6):51–63.
Yin, J., Goh, T.-T., and Hu, Y. (2024). Interactions with educational chatbots: the impact of induced emotions and students' learning motivation. International Journal of Educational Technology in Higher Education, 21(1):47.
Zhang, Y., Li, M., Long, D., Zhang, X., Lin, H., Yang, B., Xie, P., Yang, A., Liu, D., Lin, J., et al. (2025). Qwen3 embedding: Advancing text embedding and reranking through foundation models. arXiv preprint arXiv:2506.05176.
Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., et al. (2023). Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in neural information processing systems, 36:46595–46623.
Alario-Hoyos, C., Kemcha, R., Kloos, C. D., Callejo, P., Estévez-Ayres, I., Santín-Cristóbal, D., Cruz-Argudo, F., and López-Sánchez, J. L. (2024). Tailoring your code companion: Leveraging llms and rag to develop a chatbot to support students in a programming course. In 2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE), pages 1–8. IEEE.
Anderson, J. R., Boyle, C. F., and Reiser, B. J. (1985). Intelligent tutoring systems. Science, 228(4698):456–462.
Anthropic (2026). Claude 4.7 opus. Software / LLM. Versão 4.7.
Bhatia, G., Peyrard, M., and Zhao, W. (2025). Date fragments: A hidden bottleneck of tokenization for temporal reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 3201–3219.
Chroma (2022). Chroma: the ai-native open-source embedding database. [link]. Acesso em: Março de 2026.
da Costa, V. K., Zen, E., da Silva, A. B. A., and Tavares, T. A. (2023). Experiências com uso de mesa tangível em espaços de educação não formal. In Simpósio Brasileiro de Informática na Educação (SBIE), pages 983–994. SBC.
Danuarta, L., Mawardi, V. C., and Lee, V. (2024). Retrieval-augmented generation (rag) large language model for educational chatbot. In 2024 Ninth International Conference on Informatics and Computing (ICIC), pages 1–6. IEEE.
de Sousa, R. R. A., Santos, A., and Diogo, A. Q. (2023). A preservação da memória histórica na era digital: Desafios, oportunidades e tecnologias interativas no ensino e na pesquisa. Revista Inter-Ação.
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), pages 4171–4186.
Halbwachs, M. (1997). La mémoire collective. Albin Michel.
Idris, M. Z., Mustaffa, N. B., and Yusoff, S. O. S. (2016). Preservation of intangible cultural heritage using advance digital technology: Issues and challenges. Harmonia: Journal of Arts Research and Education, 16(1):1–13.
Isotani, S., Bittencourt, I. I., Challco, G. C., Dermeval, D., and Mello, R. F. (2023). Aied unplugged: Leapfrogging the digital divide to reach the underserved. In International Conference on Artificial Intelligence in Education, pages 772–779. Springer.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–9474.
Liu, Z., Agrawal, P., Singhal, S., Madaan, V., Kumar, M., and Verma, P. K. (2025). Lpi-tutor: an llm based personalized intelligent tutoring system using rag and prompt engineering. PeerJ Computer Science, 11:e2991.
Mello, R. F., Anthony, L., Lobo, J., Ribeiro, F. G. C., Xavier, C., da Costa, N. T., Gasevic, D., and Rodrigues, L. (2025). Empowering equitable learning with llms: enhancing writing skills in low-resource contexts. In European Conference on Technology Enhanced Learning, pages 183–197. Springer.
Microsoft (2024). Markitdown: Python tool for converting various files to markdown. [link].
Nora, P. and Erll, A. (1997). Les lieux de mémoire, volume 3. Gallimard Paris.
Ollama (2023). Ollama. [link]. Acesso em: Março de 2026.
Streamlit (2019). Streamlit: A faster way to build and share data apps. [link]. Acesso em: Março de 2026.
Team, G., Kamath, A., Ferret, J., Pathak, S., Vieillard, N., et al. (2025). Gemma 3 technical report. arXiv.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.
Wang, S., Xu, T., Li, H., Zhang, C., Liang, J., Tang, J., Yu, P. S., and Wen, Q. (2026). Large language models for education: A survey and outlook. IEEE Signal Processing Magazine, 42(6):51–63.
Yin, J., Goh, T.-T., and Hu, Y. (2024). Interactions with educational chatbots: the impact of induced emotions and students' learning motivation. International Journal of Educational Technology in Higher Education, 21(1):47.
Zhang, Y., Li, M., Long, D., Zhang, X., Lin, H., Yang, B., Xie, P., Yang, A., Liu, D., Lin, J., et al. (2025). Qwen3 embedding: Advancing text embedding and reranking through foundation models. arXiv preprint arXiv:2506.05176.
Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., et al. (2023). Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in neural information processing systems, 36:46595–46623.
Publicado
05/10/2026
Como Citar
AQUINI, Lui Gill; RIBEIRO, Marcelo Clasen; DIAS, Marcelo da Silva; JURGINA, Laura Quevedo; DE AGUIAR, Marilton Sanchotene; DA ROSA JUNIOR, Leomar Soares.
Lugares de Memória Digitais: um Sistema Tutor Inteligente Baseado em RAG para a Preservação da História de Pelotas. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 1489-1501.
DOI: https://doi.org/10.5753/sbie.2026.27891.
