Better To Ask in English? Evaluating Factual Accuracy of Multilingual LLMs in English and Low-Resource Languages
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909785195020288 |
|---|---|
| author | Rohera, Pritika Ginimav, Chaitrali Sawant, Gayatri Joshi, Raviraj |
| author_facet | Rohera, Pritika Ginimav, Chaitrali Sawant, Gayatri Joshi, Raviraj |
| contents | Multilingual Large Language Models (LLMs) have demonstrated significant effectiveness across various languages, particularly in high-resource languages such as English. However, their performance in terms of factual accuracy across other low-resource languages, especially Indic languages, remains an area of investigation. In this study, we assess the factual accuracy of LLMs - GPT-4o, Gemma-2-9B, Gemma-2-2B, and Llama-3.1-8B - by comparing their performance in English and Indic languages using the IndicQuest dataset, which contains question-answer pairs in English and 19 Indic languages. By asking the same questions in English and their respective Indic translations, we analyze whether the models are more reliable for regional context questions in Indic languages or when operating in English. Our findings reveal that LLMs often perform better in English, even for questions rooted in Indic contexts. Notably, we observe a higher tendency for hallucination in responses generated in low-resource Indic languages, highlighting challenges in the multilingual understanding capabilities of current LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20022 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Better To Ask in English? Evaluating Factual Accuracy of Multilingual LLMs in English and Low-Resource Languages Rohera, Pritika Ginimav, Chaitrali Sawant, Gayatri Joshi, Raviraj Computation and Language Machine Learning Multilingual Large Language Models (LLMs) have demonstrated significant effectiveness across various languages, particularly in high-resource languages such as English. However, their performance in terms of factual accuracy across other low-resource languages, especially Indic languages, remains an area of investigation. In this study, we assess the factual accuracy of LLMs - GPT-4o, Gemma-2-9B, Gemma-2-2B, and Llama-3.1-8B - by comparing their performance in English and Indic languages using the IndicQuest dataset, which contains question-answer pairs in English and 19 Indic languages. By asking the same questions in English and their respective Indic translations, we analyze whether the models are more reliable for regional context questions in Indic languages or when operating in English. Our findings reveal that LLMs often perform better in English, even for questions rooted in Indic contexts. Notably, we observe a higher tendency for hallucination in responses generated in low-resource Indic languages, highlighting challenges in the multilingual understanding capabilities of current LLMs. |
| title | Better To Ask in English? Evaluating Factual Accuracy of Multilingual LLMs in English and Low-Resource Languages |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2504.20022 |