Soft Prompt-Tuning for Plant Pest and Disease Classification from Colloquial Descriptions

Xinlu LiuXinbing Li^*Yi Zhu

• Yangzhou University, Yangzhou, China

The precise identification of plant pests and diseases plays a crucial role in preserving crop health and optimizing agricultural productivity. In practice, however, farmers frequently report symptoms in informal, everyday language. Traditional intelligent farming assistants are built upon domain-specific classification frameworks that depend on formal terminologies and structured symptom inputs, leading to subpar performance when faced with natural, unstructured farmer descriptions. To address this issue, we propose an innovative approach that classifies plant pests and diseases from colloquial symptom reports by leveraging soft prompt-tuning. Initially, we utilize Pre-trained Language Models (PLMs) to conduct named entity recognition and retrieve domain-specific knowledge to enrich the input. Notably, this knowledge enrichment process introduces a kind of semantic alignment between the colloquial input and the acquired knowledge, enabling the model to better align informal expressions with formal agricultural concepts. Next, we apply a soft prompt-tuning strategy coupled with an external knowledge-enhanced verbalizer for the classification task. Our experiments demonstrate that this approach outperforms baseline approaches, including state-of-the-art(SOTA) large language models (LLMs). The results highlight the potential of prompt-tuning methods in bridging the gap between colloquial descriptions and expert knowledge, offering practical implications for the development of more accessible and intelligent agricultural support systems.