CRSLLM: A Hybrid Conversational Recommender System Integrating Collaborative Filtering and Large Language Models
Resumo
Sistemas de Recomendação Conversacionais ampliam os sistemas de recomendação tradicionais ao incorporar informações obtidas durante a interação com o usuário. Este trabalho propõe o CRSLLM, uma arquitetura híbrida que integra filtragem colaborativa e LLMs para extração automática do perfil do usuário, geração zero-shot e refinamento contextual das recomendações. O sistema utiliza o algoritmo EASE como núcleo de recomendação e instâncias do ChatGPT (gpt-4o-mini), priorizando uma arquitetura modular e de baixa complexidade computacional. Os experimentos na base ReDial demonstraram alta efetividade na extração de preferências e melhorias nas métricas Recall@K e NDCG@K em relação ao método base, além de desempenho competitivo frente a abordagens recentes baseadas em LLMs.
Referências
Chen, Q., Lin, J., Zhang, Y., Ding, M., Cen, Y., Yang, H., and Tang, J. (2019). Towards knowledge-based recommender dialog system. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP).
Christakopoulou, K., Radlinski, F., and Hofmann, K. (2016). Towards conversational recommender systems. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 815–824. ACM.
Ding, X., Yu, W., Xie, Y., and Liu, S. (2020). Efficient model-based collaborative filtering with fast adaptive pca. arXiv preprint arXiv:2009.02251.
Gao, C. et al. (2021). Advances and challenges in conversational recommender systems. Journal of Information Processing.
He, Z., Xie, Z., Jha, R., Steck, H., Liang, D., Feng, Y., Majumder, B. P., Kallus, N., and McAuley, J. (2023). Large language models as zero-shot conversational recommenders. In Proceedings of the 32nd ACM International CIKM.
Jannach, D., Manzoor, A., Cai, W., and Chen, L. (2021). A survey on conversational recommender systems. ACM Computing Surveys, 54(4):105:1–105:35.
Li, R., Kahou, S. E., Schulz, H., Michalski, V., Charlin, L., and Pal, C. (2018). Towards deep conversational recommendations. In Advances in Neural Information Processing Systems 31 (NIPS 2018).
Liang, T., Jin, C., Wang, L., Fan, W., Xia, C., Chen, K., and Yin, Y. (2024). LLM-REDIAL: A large-scale dataset for conversational recommender systems created from user behaviors with LLMs. pages 8926–8939, Bangkok, Thailand. Association for Computational Linguistics.
Roy, D. and Dutta, M. (2022). A systematic review and research perspective on recommender systems. Journal of Big Data, 9(1):59.
Steck, H. (2019). Embarrassingly shallow autoencoders for sparse data. In Proceedings of The Web Conference (WWW), pages 3251–3257. ACM.
Sun, Y. and Zhang, Y. (2018). Conversational recommender system. In Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pages 235–244, Ann Arbor, MI, USA. ACM.
Tran, D. H., Sheng, Q. Z., Zhang, W. E., Hamad, S. A., Zaib, M., Tran, N. H., Yao, L., and Khoa, N. L. D. (2020). Deep conversational recommender system: A new frontier for goal-oriented dialogue systems. arXiv preprint arXiv:2004.13245.
Wang, X., Tang, X., Zhao, W. X., Wang, J., and Wen, J.-R. (2023). Rethinking the evaluation for conversational recommendation in the era of large language models. arXiv preprint arXiv:2305.13112.
Wang, X., Zhou, K., Wen, J.-R., and Zhao, W. X. (2022). Towards unified conversational recommender systems via knowledge-enhanced prompt learning. In Proc. of the 28th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining, pages 1929–1937.
Zhao, Z., Fan, W., Li, J., Liu, Y., Mei, X., Wang, Y., Wen, Z., Wang, F., Zhao, X., Tang, J., and Li, Q. (2023). Recommender systems in the era of large language models (llms). IEEE Transactions on Knowledge and Data Engineering. arXiv:2307.02046.
Zhou, K., Zhao, W. X., Bian, S., Zhou, Y., Wen, J.-R., and Yu, J. (2020). Improving conversational recommender systems via knowledge graph based semantic fusion. In Proc. of the 26th ACM SIGKDD Conf. on KDD, pages 1006–1014.
Zhu, Y., Steck, H., Liang, D., He, Y., Kallus, N., and Li, J. (2025a). Llm-based conversational recommendation agents with collaborative verbalized experience. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2207–2220.
Zhu, Y., Wan, C., Steck, H., Liang, D., Feng, Y., Kallus, N., and Li, J. (2025b). Collaborative retrieval for large language model-based conversational recommender systems. In Proceedings of the ACM Web Conference 2025, WWW ’25. ACM.
Christakopoulou, K., Radlinski, F., and Hofmann, K. (2016). Towards conversational recommender systems. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 815–824. ACM.
Ding, X., Yu, W., Xie, Y., and Liu, S. (2020). Efficient model-based collaborative filtering with fast adaptive pca. arXiv preprint arXiv:2009.02251.
Gao, C. et al. (2021). Advances and challenges in conversational recommender systems. Journal of Information Processing.
He, Z., Xie, Z., Jha, R., Steck, H., Liang, D., Feng, Y., Majumder, B. P., Kallus, N., and McAuley, J. (2023). Large language models as zero-shot conversational recommenders. In Proceedings of the 32nd ACM International CIKM.
Jannach, D., Manzoor, A., Cai, W., and Chen, L. (2021). A survey on conversational recommender systems. ACM Computing Surveys, 54(4):105:1–105:35.
Li, R., Kahou, S. E., Schulz, H., Michalski, V., Charlin, L., and Pal, C. (2018). Towards deep conversational recommendations. In Advances in Neural Information Processing Systems 31 (NIPS 2018).
Liang, T., Jin, C., Wang, L., Fan, W., Xia, C., Chen, K., and Yin, Y. (2024). LLM-REDIAL: A large-scale dataset for conversational recommender systems created from user behaviors with LLMs. pages 8926–8939, Bangkok, Thailand. Association for Computational Linguistics.
Roy, D. and Dutta, M. (2022). A systematic review and research perspective on recommender systems. Journal of Big Data, 9(1):59.
Steck, H. (2019). Embarrassingly shallow autoencoders for sparse data. In Proceedings of The Web Conference (WWW), pages 3251–3257. ACM.
Sun, Y. and Zhang, Y. (2018). Conversational recommender system. In Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pages 235–244, Ann Arbor, MI, USA. ACM.
Tran, D. H., Sheng, Q. Z., Zhang, W. E., Hamad, S. A., Zaib, M., Tran, N. H., Yao, L., and Khoa, N. L. D. (2020). Deep conversational recommender system: A new frontier for goal-oriented dialogue systems. arXiv preprint arXiv:2004.13245.
Wang, X., Tang, X., Zhao, W. X., Wang, J., and Wen, J.-R. (2023). Rethinking the evaluation for conversational recommendation in the era of large language models. arXiv preprint arXiv:2305.13112.
Wang, X., Zhou, K., Wen, J.-R., and Zhao, W. X. (2022). Towards unified conversational recommender systems via knowledge-enhanced prompt learning. In Proc. of the 28th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining, pages 1929–1937.
Zhao, Z., Fan, W., Li, J., Liu, Y., Mei, X., Wang, Y., Wen, Z., Wang, F., Zhao, X., Tang, J., and Li, Q. (2023). Recommender systems in the era of large language models (llms). IEEE Transactions on Knowledge and Data Engineering. arXiv:2307.02046.
Zhou, K., Zhao, W. X., Bian, S., Zhou, Y., Wen, J.-R., and Yu, J. (2020). Improving conversational recommender systems via knowledge graph based semantic fusion. In Proc. of the 26th ACM SIGKDD Conf. on KDD, pages 1006–1014.
Zhu, Y., Steck, H., Liang, D., He, Y., Kallus, N., and Li, J. (2025a). Llm-based conversational recommendation agents with collaborative verbalized experience. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2207–2220.
Zhu, Y., Wan, C., Steck, H., Liang, D., Feng, Y., Kallus, N., and Li, J. (2025b). Collaborative retrieval for large language model-based conversational recommender systems. In Proceedings of the ACM Web Conference 2025, WWW ’25. ACM.
Publicado
19/10/2026
Como Citar
PRUDÊNCIO, Marcos André de Barros; BEZERRA, Byron Leite Dantas.
CRSLLM: A Hybrid Conversational Recommender System Integrating Collaborative Filtering and Large Language Models. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 2859-2870.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.30765.
