Vichat: summary-augmented contextual retrieval for Vietnamese intangible cultural heritage question answering
,
,
and
*
Article Sidebar
Full Text: 
PDF
Main Article Content
Abstract
Retrieval-augmented generation over cultural heritage archives is undermined by semantic isolation; fixed-size chunking strips the topic, temporal, and geographic context that makes a passage interpretable, so a chunk reading recognized as national heritage in 2014 no longer identifies which festival or province it describes. Contextual Retrieval repairs this by having an LLM contextualize each chunk, but at one LLM call per chunk. We propose Summary-Augmented Contextual Retrieval (SACR), which summarizes each document once and prepends that single summary to all of its chunks before indexing, reducing cost to one call per document. We further release ViCH-QA, an expert-validated benchmark of 4,719 Vietnamese question-answer (QA) pairs over 159 documents spanning 18 intangible cultural heritage (ICH) topics of Southern Vietnam. Evaluating lexical, dense, and hybrid retrievers under two Vietnamese word segmenters and an unsegmented baseline, we find that SACR raises NDCG@10 in all six matched configurations tested, most sharply for unreranked BM25 (+0.0394), reaching 0.8840 at best. The improvement reflects an inherent trade-off: SACR concentrates relevant passages at the top of the ranking while slightly reducing Hit@10, which is favorable for downstream generation but less suited for broad recall-oriented retrieval. Across six open-source generator backbones, the optimal pipeline is invariably SACR with reranking and few-shot prompting, peaking at a token-F1 of 0.5560; since SACR’s cost is paid offline and few-shot prompting is faster than chain-of-thought, our most accurate configuration is also among the cheapest to serve.
Article Details
Conflict of Interest
© 2026 The authors. This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License.
References
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., & others. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877–1901.
Cormack, G. V., Clarke, C. L. A., & Buettcher, S. (2009). Reciprocal rank fusion outperforms condorcet and individual rank learning methods. Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’09, 758–759. https://doi.org/10.1145/1571941.1572114
Do, P., Phan, T. H. V., & Gupta, B. B. (2021). Developing a Vietnamese Tourism Question Answering System Using Knowledge Graph and Deep Learning. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 20(5), 1-18. https://doi.org/10.1145/3453651
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023). Survey of Hallucination in Natural Language Generation. ACM Comput. Surv., 55(12), 1-38. https://doi.org/10.1145/3571730
Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C. H., Gonzalez, J. E., Zhang, H., & Stoica, I. (2023). Efficient Memory Management for Large Language Model Serving with PagedAttention. Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles (pp. 611 - 6). https://doi.org/10.1145/3600006.3613165
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W., Rocktäschel, T., & others. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33, 9459–9474.
Lin, C.-Y. (2004). ROUGE: A Package for Automatic Evaluation of Summaries. Text Summarization Branches Out, 74–81.
Nguyen, H.-D., Dang, M.-A., Le, M.-T., & Le, M.-T. (2025). VietMEAgent: Culturally-Aware Few-Shot Multimodal Explanation for Vietnamese Visual Question Answering. arXiv Preprint arXiv:2511.09058.
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2002). Bleu: A Method for Automatic Evaluation of Machine Translation. In P. Isabelle, E. Charniak, & D. Lin (Eds.), Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (pp. 311–318). Association for Computational Linguistics. https://doi.org/10.3115/1073083.1073135
Peoples, S. (2014). Intangible heritage and the museum: New perspective on cultural preservation. International Journal of Heritage Studies, 20(5), 579–581. https://doi.org/10.1080/13527258.2014.913343
Robertson, S., & Zaragoza, H. (2009). The Probabilistic Relevance Framework: BM25 and Beyond. Found. Trends Inf. Retr., 3(4), 333–389. https://doi.org/10.1561/1500000019
Sun, J., Shi, J., Xie, Y., Wang, S., Parekh, J. R., Jiang, P., Shi, Z., Fan, J., Zheng, Q., Li, P., Wang, S., Liu, G., & Han, J. (2026). Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation.
Tao, W., Xing, X., Li, Z., & Xu, X. (2025). SAKI-RAG: Mitigating Context Fragmentation in Long-Document RAG via Sentence-level Attention Knowledge Integration. In C. Christodoulopoulos, T. Chakraborty, C. Rose, & V. Peng (Eds.), Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (pp. 1195–1213). Association for Computational Linguistics. https://doi.org/10.18653/v1/2025.emnlp-main.63
Trivedi, H., Balasubramanian, N., Khot, T., & Sabharwal, A. (2023). Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions. In A. Rogers, J. Boyd-Graber, & N. Okazaki (Eds.), Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 10014–10037). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.acl-long.557
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., & others. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837. https://doi.org/10.52202/068431-1800
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2020). BERTScore: Evaluating Text Generation with BERT. International Conference on Learning Representations.