Research on Sem-RAG: A Corn Planting Knowledge Question-Answering Algorithm Based on Fine-Grained Semantic Information Retrieval Enhancement
Source abstract
Abstract
Large language models and retrieval-augmented generation (RAG) are widely applied in knowledge question-answering tasks. However, in knowledge-intensive domains such as agriculture, hallucination and insufficient retrieval accuracy remain challenging. To address these issues, we propose Sem-RAG, a corn planting knowledge question-answering algorithm based on fine-grained semantic retrieval enhancement. Unlike standard NaiveRAG, which retrieves only fixed-length text chunks, and GraphRAG, which relies solely on graph node connections, Sem-RAG introduces a dual-store retrieval mechanism. It constructs both a surface semantic store (chunk-level embeddings) and a fine-grained semantic store derived from Leiden-based community summaries. These community summaries do not merely shorten contexts; instead, they provide thematic-level semantic aggregation across document chunks, thereby enhancing semantic coverage and reducing noise. During retrieval, user queries are matched against the surface store to locate relevant chunks and simultaneously linked to corresponding thematic summaries in the fine-grained store, ensuring that both local details and higher-level associations are leveraged. We evaluated Sem-RAG on the corn knowledge question-answering dataset CornData. The algorithm achieved Answer-C, Answer-R, and CR scores of 94.6%, 84.6%, and 70.4%, respectively, which were 2.6%, 1.7%, and 1.6% higher than those of traditional NaiveRAG. These results demonstrate that Sem-RAG materially improves the quality and reliability of agricultural knowledge Q&A by combining dual-store retrieval with community-level semantic aggregation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Web Data Mining and Analysis · Natural Language Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer and Information Engineering, Xinjiang Agricultural University, Urumqi 830052, China
Ministry of Education, Engineering Research Center for Intelligent Agriculture, Urumqi 830052, China
Xinjiang Agricultural Informatization Engineering Technology Research Center, Urumqi 830052, China
Funding
the National Key R&D Program of China · the Provincial Key S&T Program of Xinjiang
References (40)
Show source-provided references
1. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, Neural Information Processing Systems Foundation, Inc. (NeurIPS).
2. A primer in BERTology: What we know about how BERT works10.1162/tacl_a_00349 ↗
3. Language models are unsupervised multitask learners
4. Exploring the limits of transfer learning with a unified text-to-text transformer
5. Palm: Scaling language modeling with pathways
6. Yang, H., Chen, H., Guo, H., Li, X., Wang, Y., Zhang, Y., Liu, Y., and Xie, X. (2024). Llm-medqa: Enhancing medical question answering through case studies in large language models. arXiv.
7. LLM based QA chatbot builder: A generative AI-based chatbot builder for question answering10.1016/j.softx.2024.102029 ↗
8. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions
9. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.T., and Rocktäschel, T. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, Neural Information Processing Systems Foundation, Inc. (NeurIPS).
10. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., and Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv.
11. Fang, Y., Zhan, J., Ai, Q., Chen, J., Ouyang, S., and Zhao, W.X. (2024, January 14–18). Scaling laws for dense retrieval. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Washington, DC, USA.10.1145/3626772.3657743 ↗
12. Fan, W., Ding, Y., Ning, L., Wang, S., He, Y., Wang, Y., Yin, D., Wang, C., and Zhang, D. (2024, January 25–29). A survey on rag meeting llms: Towards retrieval-augmented large language models. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain.10.1145/3637528.3671470 ↗
13. Sentiment enhanced answer generation and information fusing for product-related question answering10.1016/j.ins.2023.01.098 ↗
14. Tam, D., Menon, R.R., Bansal, M., Srivastava, S., and Raffel, C. (2021). Improving and simplifying pattern exploiting training. arXiv.10.18653/v1/2021.emnlp-main.407 ↗
15. Oche, A.J., Folashade, A.G., Ghosal, T., Saha, S., and Ekpo, R.H. (2025). A systematic review of key retrieval-augmented generation (rag) systems: Progress, gaps, and future directions. arXiv.
16. Almanac—Retrieval-augmented language models for clinical medicine10.1056/AIoa2300068 ↗
17. The Role of Retrieval-Augmented Generation (RAG) in Financial Document Processing: Automating Compliance and Reporting
18. Su, W., Tang, Y., Ai, Q., Mao, J., Liu, Y., and Zhao, W.X. (2025, January 13–18). Parametric retrieval augmented generation. Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Padua, Italy.10.1145/3726302.3731692 ↗
19. Ding, W., Cao, Y., Zhao, D., Bärgman, J., and Huang, C. (2024). Realgen: Retrieval augmented generation for controllable traffic scenarios. European Conference on Computer Vision, Springer Nature.10.1007/978-3-031-73033-7_6 ↗
20. Wang, H., Prasad, A., Stengel-Eskin, E., and Bansal, M. (2025). Retrieval-augmented generation with conflicting evidence. arXiv.
21. Béchard, P., and Ayala, O.M. (2024). Reducing hallucination in structured outputs via Retrieval-Augmented Generation. arXiv.
22. Shao, Z., Gong, Y., Shen, Y., Huang, M., Duan, N., and Chen, W. (2023). Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. arXiv.10.18653/v1/2023.findings-emnlp.620 ↗
23. Ovadia, O., Brief, M., Mishaeli, M., and Elisha, O. (2023). Fine-tuning or retrieval? comparing knowledge injection in llms. arXiv.10.18653/v1/2024.emnlp-main.15 ↗
24. Amugongo, L.M., Mascheroni, P., Brooks, S., Bidarmaghz, A., Kifle, M., Kaluza, B., and Celik, T. (2025). Retrieval augmented generation for large language models in healthcare: A systematic review. PLoS Digit. Health, 4.10.1371/journal.pdig.0000877 ↗
25. Zhuang, Y., Yu, Y., Wang, K., Sun, H., and Shi, C. (2023). Toolqa: A dataset for llm question answering with external tools. Advances in Neural Information Processing Systems, Neural Information Processing Systems Foundation, Inc. (NeurIPS).
26. Wu, J., Zhu, J., Qi, Y., Sun, Z., He, X., Xie, X., Xu, H., Chen, Y., Zhang, Y., and Xing, Z. (2024). Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation. arXiv.10.18653/v1/2025.acl-long.1381 ↗
27. Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2022, January 25–29). Lora: Low-rank adaptation of large language models. Proceedings of the 2022 International Conference on Learning Representations, Online.
28. Li, Y., Yu, Y., Liang, C., He, P., Karampatziakis, N., Chen, W., and Zhao, T. (2023). Loftq: Lora-fine-tuning-aware quantization for large language models. arXiv.
29. Mao, Y., Ge, Y., Fan, Y., Ma, C., Wang, Z., Sun, R., Lou, J.G., and Zhang, D. (2025). A survey on lora of large language models. Front. Comput. Sci., 19.10.1007/s11704-024-40663-9 ↗
30. A Comprehensive Review on Text Detection and Recognition in Scene Images
31. Advancements in OCR: A deep learning algorithm for enhanced text recognition
32. The anatomy of a large-scale hypertextual web search engine10.1016/S0169-7552(98)00110-X ↗
33. Mirtaheri, S.M., Dinçktürk, M.E., Hooshmand, S., Bochmann, G.V., Jourdan, G.V., and Onut, I.V. (2014). A brief history of web crawlers. arXiv.
34. Lotfi, C., Srinivasan, S., Ertz, M., and Latrous, I. (2021). Web Scraping Techniques and Applications: A Literature. SCRS Conference Proceedings on Intelligent Systems, SCRS Publications.10.52458/978-93-91842-08-6-38 ↗
35. Goutte, C., and Gaussier, E. (2005). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. European Conference on Information Retrieval, Springer.10.1007/978-3-540-31865-1_25 ↗
36. Saracevic, T. (1995, January 9–13). Evaluation of evaluation in information retrieval. Proceedings of the 18th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Seattle, WA, USA.10.1145/215206.215351 ↗
37. Es, S., James, J., Anke, L.E., and Schockaert, S. (2024, January 17–22). Ragas: Automated evaluation of retrieval augmented generation. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, St. Julians, Malta.10.18653/v1/2024.eacl-demo.16 ↗
38. Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., and Dyer, C. (2016). Neural architectures for named entity recognition. arXiv.10.18653/v1/N16-1030 ↗
39. Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2–7). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA.
40. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv.