Are Re-Ranking in Retrieval-Augmented Generation Methods Impactful for Small Agriculture QA Datasets? A Small Experiment

Open Access

Issue		BIO Web Conf. Volume 167, 2025 5^th International Conference on Smart and Innovative Agriculture (ICoSIA 2024)


Article Number		01001
Number of page(s)		6
Section		Agricultural Big Data Analysis
DOI		https://doi.org/10.1051/bioconf/202516701001
Published online		19 March 2025

G. Blanchy, G. Bragato, C. Di Bene, N. Jarvis, M. Larsbo, K. Meurer, S. Garré, Soil and crop management practices and the water regulation functions of soils: a qualitative synthesis of metaanalyses relevant to European agriculture. SOIL 9, 1–20 (2023). https://doi.org/10.5194/soil-9-1-2023. [Google Scholar]
L. Hu, Z. Liu, Z. Zhao, L. Hou, L. Nie, J. Li, A survey of knowledge enhanced pre-trained language models. IEEE Trans. Knowl. Data Eng. 36, 1413–1430 (2024). https://doi.org/10.1109/TKDE.2023.3310002. [CrossRef] [Google Scholar]
M. Lewenstein, A. Gratsea, A. Riera-Campeny, A. Aloy, V. Kasper, A. Sanpera, Storage capacity and learning capability of quantum neural networks. Quantum Sci. Technol. 6, 045002 (2021). https://doi.org/10.1088/2058-9565/ac070f. [Google Scholar]
A. Fan, C. Gardent, C. Braud, A. Bordes, Augmenting transformers with KNN-based composite memory for dialog. Trans. Assoc. Comput. Linguist. 9, 82–99 (2021). https://doi.org/10.1162/tada00356. [Google Scholar]
A. Scalercio, A. Paes, Masked transformer through knowledge distillation for unsupervised text style transfer. Nat. Lang. Eng. 30, 973–1008 (2024). https://doi.org/10.1017/S1351324923000323. [Google Scholar]
S. Siriwardhana, R. Weerasekera, E. Wen, T. Kaluarachchi, R. Rana, S. Nanayakkara, Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. Trans. Assoc. Comput. Linguist. 11, 1–17 (2023). https://doi.org/10.1162/tada00530. [Google Scholar]
Z. Ahmad, A. Ekbal, S. Sengupta, P. Bhattacharyya, Neural response generation for task completion using conversational knowledge graph. PLoS ONE 18, e0269856 (2023). https://doi.org/10.1371/joumal.pone.0269856. [Google Scholar]
U. Kamal, M. Zunaed, N. B. Nizam, T. Hasan, Anatomy-XNet: An anatomy aware convolutional neural network for thoracic disease classification in chest X-rays. IEEE J. Biomed. Health Inform. 26, 5518–5528 (2022). https://doi.org/10.1109/JBHI.2022.3199594. [CrossRef] [PubMed] [Google Scholar]
L. Zhang, Q. Zhou, CRISPR/Cas technology: A revolutionary approach for genome engineering. Sci. China Life Sci. 57, 639–640 (2014). https://doi.org/10.1007/s11427-014-4670-x. [Google Scholar]
J. Guan, F. Huang, Z. Zhao, X. Zhu, M. Huang, A knowledge-enhanced pretraining model for commonsense story generation. Trans. Assoc. Comput. Linguist. 8, 93–108 (2020). https://doi.org/10.1162/tacla00302. [Google Scholar]
O. Ram, Y. Levine, I. Dalmedigos, D. Muhlgay, A. Shashua, K. Leyton-Brown, Y. Shoham, In-context retrieval-augmented language models. Trans. Assoc. Comput. Linguist. 11, 1316–1331 (2023). https://doi.org/10.1162/tacla00605. [Google Scholar]
D. Ji, S. Zhao, G. Xiao, Chinese document reranking based on automatically acquired term resource. Lang. Resour. Eval. 43, 385–406 (2009). https://doi.org/10.1007/s10579-009-9106-z. [Google Scholar]
S. A. Seyedi, A. Lotfi, P. Moradi, N. N. Qader, Dynamic graph-based label propagation for density peaks clustering. Expert Syst. Appl. 115, 314–328 (2019). https://doi.org/10.1016/j.eswa.2018.07.075. [Google Scholar]
Y. Zhang, Q. Qian, H. Wang, C. Liu, W. Chen, F. Wang, Graph convolution based efficient reranking for visual retrieval. IEEE Trans. Multimedia 26, 1089–1101 (2024). https://doi.org/10.1109/TMM.2023.3276167. [CrossRef] [Google Scholar]
Z. Li, K. C. K. Lee, B. Zheng, W.-C. Lee, D. Lee, X. Wang, IR-Tree: An efficient index for geographic document search. IEEE Trans. Knowl. Data Eng. 23, 585–599 (2011). https://doi.org/10.1109/TKDE.2010.149. [CrossRef] [Google Scholar]
H. Yu, X. Wang, G. Wang, X. Zeng, An active three-way clustering method via low-rank matrices for multi-view data. Inf. Sci. 507, 823–839 (2020). https://doi.org/10.1016/j.ins.2018.03.009. [CrossRef] [Google Scholar]
G. Zhao, X. Zhang, Re-ranking web data per knowledge domain. Int. J. Serv. Knowl. Manag. 3, 66–84 (2019). https://doi.org/10.52731/ijskm.v3.i1.274. [Google Scholar]
D. S. Sachan, M. Lewis, D. Yogatama, L. Zettlemoyer, J. Pineau, M. Zaheer, Questions are all you need to train a dense passage retriever. Trans. Assoc. Comput. Linguist. 11, 600–616 (2023). https://doi.org/10.1162/tacla00564. [Google Scholar]
S. Godara, J. Bedi, R. Parsad, D. Singh, R. S. Bana, S. Marwaha, AgriResponse: A real-time agricultural query-response generation system for assisting nationwide farmers. IEEE Access 12, 294–311 (2024). https://doi.org/10.1109/ACCESS.2023.3339253. [CrossRef] [Google Scholar]
I. Annamoradnejad, G. Zoghi, ColBERT: Using BERT sentence embedding in parallel neural networks for computational humor. Expert Syst. Appl. 249, 123685 (2024). https://doi.org/10.1016/j.eswa.2024.123685. [CrossRef] [Google Scholar]
KisanVaani/agriculture-qa-english-only • Datasets at Hugging Face [Online]. 2024. https://huggingface.co/datasets/KisanVaani/agriculture-qa-english-only [11 Mar. 2024]. [Google Scholar]
Johnson, M. Douze, H. Jegou, Billion-scale similarity search with GPUs. IEEE Trans. Big Data 7, 535–547 (2021). https://doi.org/10.1109/TBDATA.2019.2921572. [CrossRef] [Google Scholar]
M. G. Sohrab, M. Asada, M. Rikters, M. Miwa, BERT-NAR-BERT: A non-autoregressive pretrained sequence-to-sequence model leveraging BERT checkpoints. IEEE Access 12, 23–33 (2024). https://doi.org/10.1109/ACCESS.2023.3346952. [CrossRef] [Google Scholar]
Z. Sun, G. Pedretti, E. Ambrosi, A. Bricalli, D. Ielmini, In-memory eigenvector computation in time O (1). Adv. Intell. Syst. 2, 2000042 (2020). https://doi.org/10.1002/aisy.202000042. [CrossRef] [Google Scholar]
I. Yang, X. Huang, Y. Li, H. Zhou, Y. Yu, H. Bao, J. Li, S. Ren, F. Wang, L. Ye, Y. He, J. Chen, G. Pu, X. Li, X. Miao, Self-selective memristor- enabled in-memory search for highly efficient data mining. InfoMat 5, e12416 (2023). https://doi.org/10.1002/inf2.12416. [CrossRef] [Google Scholar]
S. Robertson, H. Zaragoza, The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retr. 3, 333–389 (2009). https://doi.org/10.1561/1500000019. [CrossRef] [Google Scholar]
Q. H. Ngo, T. Kechadi, N.-A. Le-Khac, OAK: Ontology-based knowledge map model for digital agriculture, in Future Data and Security Engineering, edited by T. K. Dang, J. Küng, M. Takizawa, T. M. Chung (Springer International Publishing, 2023), pp. 245–259. [Google Scholar]

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.