Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912977276370944 |
|---|---|
| author | Catalan, Carlos Rafael Monderin, Patricia Nicole Dizon, Lheane Marie Estrella, Gap Sarmimento, Raymund John Patalagsa, Marie Antoinette |
| author_facet | Catalan, Carlos Rafael Monderin, Patricia Nicole Dizon, Lheane Marie Estrella, Gap Sarmimento, Raymund John Patalagsa, Marie Antoinette |
| contents | 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 when 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18873 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo Catalan, Carlos Rafael Monderin, Patricia Nicole Dizon, Lheane Marie Estrella, Gap Sarmimento, Raymund John Patalagsa, Marie Antoinette Computation and Language Artificial Intelligence Human-Computer Interaction 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 when 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. |
| title | Evaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo |
| topic | Computation and Language Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2603.18873 |