Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.18873v1</id>\n    <title>Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo</title>\n    <updated>2026-03-19T13:17:50Z</updated>\n    <link href='https://arxiv.org/abs/2603.18873v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.18873v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Popular language learning applications such as Duolingo use large language models (LLMs) to generate lessons for its users. Most lessons focus on general real-world scenarios such as greetings, ordering food, or asking directions, with limited support for profession-specific contexts. This gap can hinder learners from achieving professional-level fluency, which we define as the ability to communicate comfortably various work-related and domain-specific information in the target language. We surveyed five employees from a multinational company in the Philippines on their experiences with Duolingo. Results show that respondents encountered general scenarios more frequently than work-related ones, and that the former are relatable and effective in building foundational grammar, vocabulary, and cultural knowledge. The latter helps bridge the gap toward professional fluency as it contains domain-specific vocabulary. Each participant suggested lesson scenarios that diverge in contexts hen analyzed in aggregate. With this understanding, we propose that language learning applications should generate lessons that adapt to an individual's needs through personalized, domain specific lesson scenarios while maintaining foundational support through general, relatable lesson scenarios.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <published>2026-03-19T13:17:50Z</published>\n    <arxiv:comment>5 pages,3 figures,presented at the 3rd HEAL Workshop at CHI 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Carlos Rafael Catalan</name>\n    </author>\n    <author>\n      <name>Patricia Nicole Monderin</name>\n    </author>\n    <author>\n      <name>Lheane Marie Dizon</name>\n    </author>\n    <author>\n      <name>Gap Estrella</name>\n    </author>\n    <author>\n      <name>Raymund John Sarmimento</name>\n    </author>\n    <author>\n      <name>Marie Antoinette Patalagsa</name>\n    </author>\n  </entry>"
}