Individual and Combined Effects of English as a Second Language and Typos on LLM Performance
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913007723872256 |
|---|---|
| author | Liu, Serena Yang, Yutong Sheth, Prisha Dong, Weixuan Diao, Mingjiao Zhu, Xinru Banga, Nikhil Melendez, Oscar Sharma, Arnav Zhao, Minda Lin, Marina Wang, Mengyu |
| author_facet | Liu, Serena Yang, Yutong Sheth, Prisha Dong, Weixuan Diao, Mingjiao Zhu, Xinru Banga, Nikhil Melendez, Oscar Sharma, Arnav Zhao, Minda Lin, Marina Wang, Mengyu |
| contents | Large language models (LLMs) are used globally, and because much of their training data is in English, they typically perform best on English inputs. As a result, many non-native English speakers interact with them in English as a second language (ESL), and these inputs often contain typographical errors. Prior work has largely studied the effects of ESL variation and typographical errors separately, even though they often co-occur in real-world use. In this study, we use the Trans-EnV framework to transform standard English inputs into eight ESL variants and apply MulTypo to inject typos at three levels: low, moderate, and severe. We find that combining ESL variation and typos generally leads to larger performance drops than either factor alone, though the combined effect is not simply additive. This pattern is clearest on closed-ended tasks, where performance degradation can be characterized more consistently across ESL variants and typo levels, while results on open-ended tasks are more mixed. Overall, these findings suggest that evaluations on clean standard English may overestimate real-world model performance, and that evaluating ESL variation and typographical errors in isolation does not fully capture model behavior in realistic settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04723 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Individual and Combined Effects of English as a Second Language and Typos on LLM Performance Liu, Serena Yang, Yutong Sheth, Prisha Dong, Weixuan Diao, Mingjiao Zhu, Xinru Banga, Nikhil Melendez, Oscar Sharma, Arnav Zhao, Minda Lin, Marina Wang, Mengyu Computation and Language Artificial Intelligence Large language models (LLMs) are used globally, and because much of their training data is in English, they typically perform best on English inputs. As a result, many non-native English speakers interact with them in English as a second language (ESL), and these inputs often contain typographical errors. Prior work has largely studied the effects of ESL variation and typographical errors separately, even though they often co-occur in real-world use. In this study, we use the Trans-EnV framework to transform standard English inputs into eight ESL variants and apply MulTypo to inject typos at three levels: low, moderate, and severe. We find that combining ESL variation and typos generally leads to larger performance drops than either factor alone, though the combined effect is not simply additive. This pattern is clearest on closed-ended tasks, where performance degradation can be characterized more consistently across ESL variants and typo levels, while results on open-ended tasks are more mixed. Overall, these findings suggest that evaluations on clean standard English may overestimate real-world model performance, and that evaluating ESL variation and typographical errors in isolation does not fully capture model behavior in realistic settings. |
| title | Individual and Combined Effects of English as a Second Language and Typos on LLM Performance |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.04723 |