Leveraging Synthetic Data for Question Answering with Multilingual LLMs in the Agricultural Domain

ACL ARR 2026 January Submission4563 Authors

Keywords: multilingual question answering, agricultural NLP, large language models, synthetic data generation, low-resource languages, domain adaptation, fine-tuning, llm-as-a-Judge, human evaluation

Abstract: Enabling farmers to access accurate agriculture-related information in their native languages in a timely manner is crucial for the success of the agriculture field. Publicly available general-purpose Large Language Models (LLMs) typically offer generic agriculture advisories, lacking precision in local and multilingual contexts. Our study addresses this limitation by generating multilingual (English, Hindi, Punjabi) synthetic datasets from agriculture-specific documents from India and fine-tuning LLMs for the task of question answering (QA). Evaluation on human-created datasets demonstrates significant improvements in factuality, relevance, and agricultural consensus for the fine-tuned LLMs compared to the baseline counterparts.

Paper Type: Short

Research Area: Resources and Evaluation

Research Area Keywords: corpus creation, language resources, multilingual corpora, NLP datasets, evaluation, datasets for low resource languages

Contribution Types: Approaches to low-resource settings, Data resources

Languages Studied: English, Hindi, Punjabi

Submission Number: 4563