Theofrida Julius Maginga

Large language models (LLMs) are increasingly used in conversational information retrieval systems to provide direct answers to user queries. However, little is known about how LLM-generated responses behave in low-resource language settings, particularly in domain-specific contexts such as agricultural knowledge access. This study investigates whether answers produced by LLMs differ systematically from human-authored responses in a Swahili agricultural question answering task. Using a dataset of 127 maize-related questions collected through fieldwork in Morogoro, Tanzania, we compare human responses with answers generated by two conversational models, ChatGPT and Gemini. The analysis combines descriptive textual statistics, lexical similarity measures based on TF-IDF cosine similarity, and TF-IDF–based logistic regression evaluated through question-grouped cross-validation. Results show consistent differences in response length, lexical diversity, and lexical similarity, with LLM-generated answers exhibiting longer and more uniform lengths despite instructions to answer briefly. Human answers had higher raw type-token ratios, while model answers showed higher fixed-window lexical diversity. Same-question lexical similarity exceeded a mismatched-question baseline. The three-source classifier achieved 0.9633 accuracy, compared with 0.7192 using length alone and 0.8058 after matching answer lengths. These findings highlight detectable patterns associated with both verbosity and source-specific wording, providing insights for evaluating conversational information retrieval systems in low-resource agricultural environments.

Horticulture as the part of agriculture sector plays the role for food security, economic growth and nutrition improvement. In developing countries where agriculture is regarded as the backbone of most countries’ economy it draws attention for most governments as the main source of employment and livelihood for the majority. Agricultural extension has been the key facilitator for achieving high crop productivity and an enabler to knowledge resources for these countries. However, lack of clear information for vegetable cultivations, crop requirements, climatic information, pests and diseases to constantly help farmers to come up with proper potential yield of the vegetable crops reduce the potential of horticulture in improving the farmers livelihood and countries economic gain , Therefore, this study aims at bringing the ICT- enabled extension support system for farmers to help them make decision on proper ways of cultivating their crops based on locations’ and timely climatic condition.