RAG-BASED DIALOG-STATE CONVERSATIONAL RECOMMENDER FOR UKRAINIAN BOOKS
DOI:
https://doi.org/10.28925/2663-4023.2026.34.1352Keywords:
conversational recommender system, retrieval-augmented generation, dialog state, natural-language understanding, hybrid retrieval, vector search, recommendation evaluationAbstract
Finding books in digital catalogs through natural-language interaction requires a system to combine verifiable catalog constraints, less formal thematic preferences, and context accumulated across multiple conversational turns. The aim of this study is to develop and experimentally evaluate a retrieval-augmented conversational recommender with an explicit dialog state for Ukrainian-language book requests. The proposed system operates over a normalized research catalog of approximately 5,500 Ukrainian books and separates natural-language understanding (NLU), deterministic dialog policy, structured and vector retrieval, user-profile ranking, and grounded response generation. A strict intermediate frame distinguishes catalog entities from semantic preferences and preserves unresolved mentions, while the dialog manager maintains active constraints, focus, pending actions, feedback, and recommendation history. Depending on the request, the system selects structured, semantic, hybrid, similar-book, author, or profile-based retrieval. Evaluation was conducted at three complementary levels: 90 deterministic regression tests, standalone NLU assessment on 1,000 Ukrainian inputs, and 70 end-to-end (E2E) scenarios comprising 170 turns. All regression tests passed. The large language model (LLM)-based parser achieved 98.3% intent accuracy, 88.7% constraint F1, and 88.0% relaxed full-frame accuracy. In E2E evaluation, the two tested NLU configurations reached 90.59–92.94% relaxed frame accuracy, 92.94–96.47% dialog-manager subset accuracy, and 97.44% recommendation-assertion accuracy. Manual inspection of 185 recommendation-bearing outputs found no book-level mismatch among the lists actually returned. Neither configuration produced duplicate works within a recommendation list or repeated a work across turns of the same scenario. The results demonstrate that explicit state, deterministic retrieval control, and grounded generation can provide reproducible, context-aware book recommendations without delegating catalog membership or item selection to free-form generation. The architecture and evaluation protocol can be reused for other catalog-grounded conversational recommendation tasks.
Downloads
References
Adomavicius, G., & Tuzhilin, A. (2005). Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering, 17(6), 734–749. https://doi.org/10.1109/TKDE.2005.99
Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User Modeling and User-Adapted Interaction, 12(4), 331–370. https://doi.org/10.1023/A:1021240730564
Gao, C., Lei, W., He, X., de Rijke, M., & Chua, T.-S. (2021). Advances and challenges in conversational recommender systems: A survey. AI Open, 2, 100–126. https://doi.org/10.1016/j.aiopen.2021.06.002
Jannach, D., Manzoor, A., Cai, W., & Chen, L. (2021). A survey on conversational recommender systems. ACM Computing Surveys, 54(5), 1–36. https://doi.org/10.1145/3453154
Williams, J. D., Raux, A., Ramachandran, D., & Black, A. (2013). The dialog state tracking challenge. In Proceedings of the SIGDIAL 2013 Conference (pp. 404–413). https://aclanthology.org/W13-4065/
Radchenko, V., & Drushchak, N. (2025). Improving named entity recognition for low-resource languages using large language models: A Ukrainian case study. In Proceedings of the Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025) (pp. 27–35). https://doi.org/10.18653/v1/2025.unlp-1.3
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., Riedel, S., & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Advances in Neural Information Processing Systems, 33, 9459–9474. https://doi.org/10.48550/arXiv.2005.11401
Chroma. (n.d.). Configure collections. Chroma Docs. Retrieved August 4, 2026, from https://docs.trychroma.com/docs/collections/configure
Li, R., Ebrahimi Kahou, S., Schulz, H., Michalski, V., Charlin, L., & Pal, C. (2018). Towards deep conversational recommendations. Advances in Neural Information Processing Systems, 31, 9748–9758. https://doi.org/10.48550/arXiv.1812.07617
Iovine, A., Narducci, F., & Semeraro, G. (2020). Conversational recommender systems and natural language: A study through the ConveRSE framework. Decision Support Systems, 131, Article 113250. https://doi.org/10.1016/j.dss.2020.113250
Wang, X., Liu, J., & Duan, J. (2024). Improved conversational recommender system based on dialog context. Natural Language Engineering, 30(6), 1210–1228. https://doi.org/10.1017/S1351324923000451
Jannach, D. (2023). Evaluating conversational recommender systems: A landscape of research. Artificial Intelligence Review, 56, 2365–2400. https://doi.org/10.1007/s10462-022-10229-x
Herlocker, J. L., Konstan, J. A., Terveen, L. G., & Riedl, J. T. (2004). Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems, 22(1), 5–53. https://doi.org/10.1145/963770.963772
Kaminskas, M., & Bridge, D. (2017). Diversity, serendipity, novelty, and coverage: A survey and empirical analysis of beyond-accuracy objectives in recommender systems. ACM Transactions on Interactive Intelligent Systems, 7(1), 1–42. https://doi.org/10.1145/2926720
Vargas, S., & Castells, P. (2011). Rank and relevance in novelty and diversity metrics for recommender systems. In Proceedings of the Fifth ACM Conference on Recommender Systems (pp. 109–116). https://doi.org/10.1145/2043932.2043955
Gurdel. (2026). RAG-based dialog-state conversational recommender for Ukrainian books [Computer software]. GitHub. Retrieved August 17, 2026, from https://github.com/Gurdel/RAG-based-dialog-state-conversational-recommender-for-Ukrainian-books
Fkih, F. (2022). Similarity measures for collaborative filtering-based recommender systems: Review and experimental comparison. Journal of King Saud University – Computer and Information Sciences, 34(9), 7645–7669. https://doi.org/10.1016/j.jksuci.2021.09.014
OpenAI. (n.d.). Compare models. OpenAI API. Retrieved August 15, 2026, from https://developers.openai.com/api/docs/models/compare
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Максим Шевченко, Олександр Марченко
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
