The field of information retrieval (IR) has evolved significantly with the advent of Generative Information Retrieval (GenIR) models, which leverage advancements in large language models to enhance the processing of complex, open-ended queries. Unlike traditional IR systems that rely on keyword matching, GenIR models can interpret nuanced queries, generate comprehensive responses, and integrate multimodal data. This shift from traditional matching methods to generative approaches represents a paradigm shift in IR, enabling more accurate and contextually appropriate retrieval of information (Li et al., 2024[1]. This study emphasizes the transformative potential of the GenIR model in advancing IR research and practical applications. By combining retrieval and generation, the GenIR model is more effective in handling complex and open queries than traditional systems. This dual capability has a significant impact on various IR applications, especially in customer service, knowledge management, and research intensive fields, where users require detailed and contextually subtle responses. The research in this paper can better promote the development and application of GenIR models.

Wenyan Zhang. Application of GenIR Models in Complex Information Retrieval Tasks. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 12: 85-90. https://doi.org/10.25236/AJCIS.2024.071212.

[1] Li, X., Jin, J., Zhou, Y., Zhang, Y., & Zhu, Y. (2024). From matching to generation: A survey on generative information retrieval. arXiv preprint arXiv:2404.14851.

[2] Scholer, F. (2024). Adapting generative information retrieval systems to users, tasks, and scenarios. Proceedings of the 2024 Information Retrieval Conference.

[3] Huang, C. W., Kuo, T. L., Chiu, T. W., Lin, T. S., Wu, S. Y. (2024). A survey of generative information retrieval. arXiv preprint arXiv:2406.01197.

[4] Siciliani, L., Ghizzota, E., Basile, P., & Lops, P. (2024). OIE4PA: Open information extraction for the public administration. Journal of Intelligent Information Systems. Retrieved from https://link.springer.com/article/10.1007/s10844-023-00814-z

[5] Josifoski, M., et al. (2023). Exploiting asymmetry for synthetic training data generation: SynthIE and the case of information extraction. arXiv preprint arXiv:2303.04132.

[6] Whitehouse, C., Vania, C., & Aji, A. F. (2023). WebIE: Faithful and robust information extraction on the web. arXiv preprint arXiv:2305.14293.

[7] Zheng, J., & Fischer, M. (2023). BIM-GPT: A prompt-based virtual assistant framework for BIM information retrieval. arXiv preprint arXiv:2304.09333.

[8] Zhang, W. (2018). Generative adversarial nets for information retrieval: Fundamentals and advances. Proceedings of the ACM SIGIR Conference on Research & Development in Information Retrieval.

[9] Tang, Y., Zhang, R., Guo, J., & de Rijke, M. (2023). Recent advances in generative information retrieval. Proceedings of the Asia Information Retrieval Conference, ACM.

[10] Lesota, O., Rekabsaz, N., & Cohen, D. (2021). A modern perspective on query likelihood with deep generative retrieval models. Proceedings of the 2021 Conference on Information Retrieval.

[11] Josifoski, M., De Cao, N., Peyrard, M., & Petroni, F. (2021). GenIE: Generative information extraction. arXiv preprint arXiv:2112.08340.

[12] Xu, D., Chen, W., Peng, W., Zhang, C., Xu, T., & Zhao, X. (2023). Large language models for generative information extraction: A survey. arXiv preprint arXiv:2312.17617.

[13] Yenduri, G., Ramalingam, M., Selvi, G. C., & Supriya, Y. (2024). GPT—a comprehensive review on enabling technologies, potential applications, emerging challenges, and future directions. IEEE Access.

[14] Ai, Q., Bai, T., Cao, Z., Chang, Y., Chen, J., & Chen, Z. (2023). Information retrieval meets large language models: A strategic report from the Chinese IR community. AI Open.

[15] Zhu, Y., Wang, S., Liu, J., & Liu, W. (2023). Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107.

[16] Madaan, G., Asthana, S. K., & Kaur, J. (2024). Generative AI: Applications, models, challenges, opportunities, and future directions. IGI Global.

[17] Ahmed, S. F., Alam, M. S. B., Hassan, M., & Rozbu, M. R. (2023). Deep learning modeling techniques: Current progress, applications, advantages, and challenges. Artificial Intelligence Review.

[18] Bandi, A., Adapa, P. V. S. R., & Kuchi, Y. E. V. P. K. (2023). The power of generative AI: A review of requirements, models, input-output formats, evaluation metrics, and challenges. Future Internet, 15(8), 260. 

[19] Ghali, M. K. (2024). Leveraging generative AI and in-context learning to reshape human-text interaction: A novel paradigm for information retrieval. ProQuest Dissertations.