Enhancing Agricultural Decision-Making with Combined Language Models
DOI:
https://doi.org/10.63665/IJMEC.1104.01Keywords:
Agricultural Advisory System, Question Answering, Retrieval-Based Learning, Sentence Embeddings, FAISS, Information Retrieval, Natural Language Processing, Dense Vector Representation, Similarity Search, Expert Knowledge Base, Farmer Queries, Domain-Specific QA, Machine Learning, Semantic Search, Agricultural Decision Support.Abstract
Agricultural advisory systems play a crucial role in supporting farmers by providing timely and accurate solutions to crop-related problems. However, building reliable question-answering systems for agriculture is challenging due to the diverse, domain-specific, and often noisy nature of farmer queries. In this project, a retrieval-based agricultural question-answering framework is proposed to deliver accurate and trustworthy responses by leveraging historical expert-curated data. The system utilizes a pretrained sentence embedding model to convert farmer queries into dense vector representations, followed by similarity-based retrieval using FAISS to identify the most relevant past questions and their corresponding expert answers. Unlike generative models, which often produce vague or hallucinated responses, the proposed approach ensures factual correctness by reusing validated advisory content. Experiments conducted on a large farmer query dataset demonstrate that the system achieves a training accuracy of 100% and a test accuracy of 95.9%, with qualitative evaluation confirming high relevance and agricultural validity of the retrieved responses. The results indicate that retrieval-based question answering is a practical, efficient, and reliable solution for real-world agricultural advisory applications.
Downloads
References
[1] Y. Chang et al., “A survey on evaluation of large language models,” ACM Transactions on Intelligent Systems and Technology, vol. 15, no. 3, pp. 1–45, Mar. 2024.
[2] J. Howard and S. Ruder, “Universal language model fine-tuning for text classification,” arXiv preprint arXiv:1801.06146, 2018.
[3] Y. Bengio, R. Ducharme, and P. Vincent, “A neural probabilistic language model,” in Advances in Neural Information Processing Systems, vol. 13, 2000, pp. 1–11.
[4] K. Tan, “Large language models for crop yield prediction,” Technical Report, 2024.
[5] Y. Luo, X. Cai, J. Qi, D. Guo, and W. Che, “FPGA-accelerated CNN for real-time plant disease identification,” Computers and Electronics in Agriculture, vol. 207, Art. no. 107715, May 2023.
[6] Y. Xu, J. Lu, and J. Zhang, “Bridging the gap between different vocabularies for LLM ensemble,” arXiv preprint arXiv:2404.09492, 2024.
[7] T. Wang et al., “From smart farming towards unmanned farms: A new mode of agricultural production,” Agriculture, vol. 11, no. 2, p. 145, Feb. 2021.
[8] J. Li et al., “Foundation models in smart agriculture: Basics, opportunities, and challenges,” Computers and Electronics in Agriculture, vol. 222, Art. no. 109032, Jul. 2024.
[9] K. Pan, X. Zhang, and L. Chen, “Research on lightweight agricultural domain-specific large language model supporting Mandarin Chinese and Uyghur,” Applied Sciences, vol. 14, no. 13, p. 5764, Jul. 2024.
[10] J. Mahapatra and U. Garain, “Impact of model size on fine-tuned LLM performance in data-to-text generation,” arXiv preprint arXiv:2407.14088, 2024.
[11] S. B. Manir et al., “LLM-based text prediction and question answer models for aphasia speech,” IEEE Access, vol. 12, pp. 114670–114680, 2024.
[12] B. Zhao et al., “ChatAgri: Exploring potentials of ChatGPT on cross-linguistic agricultural text classification,” Neurocomputing, vol. 557, Art. no. 126708, Nov. 2023.
[13] J. Wang, “LLM-based fine-tuning data generation for relation triplet extraction,” in Proc. IEEE Int. Conf. Intelligent Systems, Aug. 2024, pp. 1–7.
[14] M. P. Geetha and D. K. Renuka, “Improving aspect-based sentiment analysis using fine-tuned BERT,” International Journal of Intelligent Networks, vol. 2, pp. 64–69, Mar. 2021.
[15] H. Wang et al., “Residual LSTM and Seq2Seq neural network based on GPT for Chinese rice-related QA system,” Agriculture, vol. 12, no. 6, p. 813, Jun. 2022.
[16] S. Rezayi et al., “AgriBERT: Knowledge-infused agricultural language models,” in Proc. IJCAI, Jul. 2022, pp. 5150–5156.
[17] J. Qing et al., “GPT-aided diagnosis on agricultural image based on light YOLOPC,” Computers and Electronics in Agriculture, vol. 213, Art. no. 108168, Oct. 2023.
[18] D. Allemang and J. Sequeda, “Increasing the LLM accuracy for question answering: Ontologies to the rescue,” arXiv preprint arXiv:2405.11706, 2024.
[19] S. Rezayi et al., “Exploring new frontiers in agricultural NLP,” IEEE Transactions on Big Data, early access, Aug. 2024.
[20] J. Kpodo, P. Kordjamshidi, and A. P. Nejadhashemi, “AgXQA: Agricultural extension question answering benchmark,” Computers and Electronics in Agriculture, vol. 225, Art. no. 109349, Oct. 2024.
[21] X. Guo et al., “Efficient agricultural question classification with BERT-enhanced DPCNN,” IEEE Access, vol. 12, pp. 109255–109268, 2024.
[22] S. Yang et al., “GPT-4 as evaluator: Evaluating LLMs on pest management,” arXiv preprint arXiv:2403.11858, 2024.
[23] S. Yadav et al., “Disruptive technologies in smart farming,” AgriEngineering, vol. 4, no. 2, pp. 424–460, May 2022.
[24] M. T. Kuska et al., “AI for crop production—Where can LLMs provide value?” Computers and Electronics in Agriculture, vol. 221, Art. no. 108924, Jun. 2024.
[25] B. Imbert et al., “Knowledge graph framework in plant research,” Frontiers in Artificial Intelligence, vol. 6, Art. no. 1191122, Aug. 2023.
[26] M. O. Topal, A. Bas, and I. van Heerden, “Exploring transformers in natural language generation,” arXiv preprint arXiv:2102.08036, 2021.
[27] H. Abburi et al., “Generative AI text classification using ensemble LLM approaches,” arXiv preprint arXiv:2309.07755, 2023.
[28] J.-J. Park and S.-J. Choi, “LLMs for enhanced agricultural meteorological recommendations,” arXiv preprint arXiv:2408.04640, 2024.
[29] X. Zhao et al., “LLMs and agricultural knowledge graphs for plant disease detection,” Agriculture, vol. 14, no. 8, p. 1359, Aug. 2024.
[30] Z. Sun, “A short survey of viewing large language models in legal aspect,” arXiv preprint arXiv:2303.09136, 2023.
