TY  - EJOU
AU  - Li, Xiaoyu 
AU  - Nie, Xiaoyi 
AU  - Gu, Ke 

TI  - TRDC-RAG for Agricultural Question Answering: A Dual-Channel Retrieval Framework with Iterative Query Rewriting
T2  - Computers, Materials \& Continua

PY  - 
VL  - 
IS  - 
SN  - 1546-2226

AB  - Retrieval-augmented generation (RAG) effectively mitigates knowledge deficits and hallucination issues in large language models (LLMs) for domain-specific question answering (QA). However, in specialized agricultural domains such as rapeseed cultivation, conventional RAG frameworks suffer from severe retrieval deviations and difficulties in handling complex relational dependencies due to highly colloquial user queries, intricate hierarchical knowledge structures, and implicit logical dependencies. To address these critical limitations, this study introduces TRDC-RAG, a dual-channel retrieval-augmented framework integrating a retrieval-feedback-driven iterative query rewriting mechanism. The proposed framework constructs a multi-layer structured agricultural knowledge base and deploys a retrieval-feedback-driven, two-round query rewriting paradigm. Specifically, a vector block consistency analysis module is developed to dynamically discriminate between strongly and weakly correlated semantic trajectories, executing differentiated weighting strategies to guide precise query reconstruction. During the retrieval phase, a dual-channel architecture operates concurrently, fusing dense vector spaces with structured knowledge graph subgraphs to seamlessly bridge unstructured contextual details and explicit relational logic. Extensive evaluations on a self-constructed rapeseed QA dataset and the benchmark WikiEval dataset via the RAGAS framework demonstrate that TRDC-RAG consistently and significantly out-performs state-of-the-art baselines, including Step-Back, Multi-Query, and RAG-Fusion. On the rapeseed domain corpus, the framework achieves state-of-the-art performance with Context Precision (0.8041), Context Recall (0.8285), Faithfulness (0.9657), and Answer Relevancy (0.9733), markedly suppressing factual hallucinations. These findings confirm that TRDC-RAG provides a robust, scalable, and highly reliable architecture for intelligent agricultural knowledge services without requiring intensive parameter fine-tuning.
KW  - Retrieval-augmented generation; agricultural question answering; large language models; query rewriting; knowledge graph; intelligent agriculture

DO  - 10.32604/cmc.2026.087090