Fusão Híbrida para Recuperação de Informação Jurídica Brasileira
Resumo
A recuperação de informação jurídica brasileira envolve regimes heterogêneos de busca que exigem simultaneamente correspondência lexical precisa e generalização semântica. Embora a recuperação híbrida seja consolidada na recuperação de informação geral, ainda não está claro quando sinais lexicais e semânticos se complementam efetivamente em coleções jurídicas brasileiras diversas. Investigamos essa questão no benchmark JUÁ, que abrange múltiplos cenários: jurisprudência, atos normativos, recuperação legislativa e perguntas tributárias. Comparamos BM25, recuperadores densos da família Qwen3, variantes ajustadas ao domínio jurídico, reranqueadores e fusão híbrida via Reciprocal Rank Fusion (RRF). Nossa hipótese é que a fusão léxico-densa oferece maior robustez ao combinar sinais complementares sem necessidade de calibração direta de scores. Os resultados mostram que sistemas baseados em RRF alcançam a melhor efetividade agregada: o modelo jurídico ajustado de 4B lidera em NDCG@10 e MRR@10, enquanto o de 8B lidera em MAP@10 e Recall@10. Testes estatísticos pareados indicam ganhos robustos do RRF sobre BM25 e parte dos modelos densos, embora não domine todos os reranqueadores individualmente. No geral, a fusão híbrida léxico-semântica revela-se uma configuração particularmente robusta para busca jurídica heterogênea.Referências
Chalkidis, I., Fergadiotis, M., Malakasiotis, P., Aletras, N., and Androutsopoulos, I. (2020). Legal-bert: The muppets straight out of law school. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2898–2904.
Chen, T., Zhang, M., Lu, J., Bendersky, M., and Najork, M. (2022). Out-of-domain semantics to the rescue! zero-shot hybrid retrieval models. In ECIR 2022, page 95–110, Berlin, Heidelberg. Springer-Verlag.
Cormack, G. V., Clarke, C. L. A., and Buettcher, S. (2009). Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 758–759. ACM.
Holm, S. (1979). A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics, 6(2):65–70.
Kamalloo, E., Thakur, N., Lassance, C., Ma, X., Yang, J.-H., and Lin, J. (2024). Resources for brewing beir: Reproducible reference models and statistical analyses. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 1431–1440, New York, NY, USA. Association for Computing Machinery.
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., and Yih, W.-t. (2020). Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 6769–6781.
Louis, A., van Dijck, G., and Spanakis, G. (2025). Know when to fuse: Investigating non-English hybrid retrieval in the legal domain. In Rambow, O., Wanner, L., Apidianaki, M., Al-Khalifa, H., Eugenio, B. D., and Schockaert, S., editors, Proceedings of the 31st International Conference on Computational Linguistics, pages 4293–4312, Abu Dhabi, UAE. Association for Computational Linguistics.
Nigam, S. K., Goel, N., and Bhattacharya, A. (2022). nigam@coliee-22: Legal case retrieval and entailment using cascading oflexical and semantic-based models. In New Frontiers in Artificial Intelligence: JSAI-IsAI 2022 Workshop, JURISIN 2022, and JSAI 2022 International Session, page 96–108.
Nogueira, R. and Cho, K. (2019). Passage re-ranking with bert.
Pereira, J., Fernandes, L., de Brito, E., Lotufo, R., and Bonifacio, L. (2026). Juá – a benchmark for information retrieval in brazilian legal text collections.
Reimers, N. and Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, pages 3982–3992.
Robertson, S. and Zaragoza, H. (2009). The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends in Information Retrieval, 3(4):333–389.
Souza, F., Nogueira, R., and Lotufo, R. (2020). Bertimbau: Pretrained bert models for brazilian portuguese. In Intelligent Systems: 9th Brazilian Conference, BRACIS 2020, pages 403–417. Springer.
Thakur, N., Reimers, N., Rücklé, A., Srivastava, A., and Gurevych, I. (2021). Beir: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks.
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Scao, T. L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A. (2020). Transformers: State-of-the-art natural language processing. In EMNLP, pages 38–45.
Zhang, Y., Li, M., Long, D., Zhang, X., Lin, H., Yang, B., Xie, P., Yang, A., Liu, D., Lin, J., Huang, F., and Zhou, J. (2025). Qwen3 embedding: Advancing text embedding and reranking through foundation models.
Chen, T., Zhang, M., Lu, J., Bendersky, M., and Najork, M. (2022). Out-of-domain semantics to the rescue! zero-shot hybrid retrieval models. In ECIR 2022, page 95–110, Berlin, Heidelberg. Springer-Verlag.
Cormack, G. V., Clarke, C. L. A., and Buettcher, S. (2009). Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 758–759. ACM.
Holm, S. (1979). A simple sequentially rejective multiple test procedure. Scandinavian Journal of Statistics, 6(2):65–70.
Kamalloo, E., Thakur, N., Lassance, C., Ma, X., Yang, J.-H., and Lin, J. (2024). Resources for brewing beir: Reproducible reference models and statistical analyses. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 1431–1440, New York, NY, USA. Association for Computing Machinery.
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., and Yih, W.-t. (2020). Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 6769–6781.
Louis, A., van Dijck, G., and Spanakis, G. (2025). Know when to fuse: Investigating non-English hybrid retrieval in the legal domain. In Rambow, O., Wanner, L., Apidianaki, M., Al-Khalifa, H., Eugenio, B. D., and Schockaert, S., editors, Proceedings of the 31st International Conference on Computational Linguistics, pages 4293–4312, Abu Dhabi, UAE. Association for Computational Linguistics.
Nigam, S. K., Goel, N., and Bhattacharya, A. (2022). nigam@coliee-22: Legal case retrieval and entailment using cascading oflexical and semantic-based models. In New Frontiers in Artificial Intelligence: JSAI-IsAI 2022 Workshop, JURISIN 2022, and JSAI 2022 International Session, page 96–108.
Nogueira, R. and Cho, K. (2019). Passage re-ranking with bert.
Pereira, J., Fernandes, L., de Brito, E., Lotufo, R., and Bonifacio, L. (2026). Juá – a benchmark for information retrieval in brazilian legal text collections.
Reimers, N. and Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, pages 3982–3992.
Robertson, S. and Zaragoza, H. (2009). The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends in Information Retrieval, 3(4):333–389.
Souza, F., Nogueira, R., and Lotufo, R. (2020). Bertimbau: Pretrained bert models for brazilian portuguese. In Intelligent Systems: 9th Brazilian Conference, BRACIS 2020, pages 403–417. Springer.
Thakur, N., Reimers, N., Rücklé, A., Srivastava, A., and Gurevych, I. (2021). Beir: A heterogeneous benchmark for zero-shot evaluation of information retrieval models. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks.
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., Davison, J., Shleifer, S., von Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Scao, T. L., Gugger, S., Drame, M., Lhoest, Q., and Rush, A. (2020). Transformers: State-of-the-art natural language processing. In EMNLP, pages 38–45.
Zhang, Y., Li, M., Long, D., Zhang, X., Lin, H., Yang, B., Xie, P., Yang, A., Liu, D., Lin, J., Huang, F., and Zhou, J. (2025). Qwen3 embedding: Advancing text embedding and reranking through foundation models.
Publicado
19/10/2026
Como Citar
SORIANO, Flávio; EVANGELISTA, Guilherme; FRANÇA, Celso; PAPPA, Gisele; MEIRA JR., Wagner; GONÇALVES, Marcos.
Fusão Híbrida para Recuperação de Informação Jurídica Brasileira. In: SIMPÓSIO BRASILEIRO DE TECNOLOGIA DA INFORMAÇÃO E DA LINGUAGEM HUMANA (STIL), 17. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 420-432.
DOI: https://doi.org/10.5753/stil.2026.26661.
