"Be My Cheese?": Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914610798395392 |
|---|---|
| author | Van Doren, Madison Ford, Casey Barajas, Jennifer VanMeter, Riley Holland, Cory |
| author_facet | Van Doren, Madison Ford, Casey Barajas, Jennifer VanMeter, Riley Holland, Cory |
| contents | We present a large-scale human evaluation benchmark for assessing cultural localisation in machine translation produced by state-of-the-art multilingual large language models (LLMs). Existing MT benchmarks emphasise token-level and grammatical accuracy, but often overlook the pragmatic and culturally grounded competencies required for real-world localisation. Building on a pilot study of 87 translations across 20 languages, we evaluate 7 multilingual LLMs across 15 target languages with 5 native-speaker raters per language. Each rater scored both full-text translations and segment-level instances of culturally nuanced language (idioms, puns, holidays, and culturally embedded concepts) on an ordinal 0-3 quality scale; segment ratings additionally included an NA option for untranslated segments.
Across full-text evaluations, mean overall quality is modest (1.68/3): GPT-5 (2.10/3), Claude Sonnet 4 (1.97/3), and Mistral Medium 3.1 (1.84/3) form the strongest tier with fewer catastrophic failures. Segment-level results show sharp category effects: holidays (2.20/3) and cultural concepts (2.19/3) translate notably better than idioms (1.65/3) and puns (1.45/3), and idioms are most likely to be left untranslated. Inter-rater reliability was assessed using Krippendorff's α and Gwet's AC2, indicating moderate agreement overall (Krippendorff's α = 0.45) with the lowest agreement for puns. These findings demonstrate a persistent gap between grammatical adequacy and cultural resonance. To our knowledge, this is the first multilingual, human-annotated benchmark focused explicitly on cultural nuance in translation and localisation. The results highlight the need for culturally informed training data, improved cross-lingual pragmatics, and evaluation frameworks that support systematic benchmarking of culturally grounded translation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04729 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | "Be My Cheese?": Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs Van Doren, Madison Ford, Casey Barajas, Jennifer VanMeter, Riley Holland, Cory Computation and Language We present a large-scale human evaluation benchmark for assessing cultural localisation in machine translation produced by state-of-the-art multilingual large language models (LLMs). Existing MT benchmarks emphasise token-level and grammatical accuracy, but often overlook the pragmatic and culturally grounded competencies required for real-world localisation. Building on a pilot study of 87 translations across 20 languages, we evaluate 7 multilingual LLMs across 15 target languages with 5 native-speaker raters per language. Each rater scored both full-text translations and segment-level instances of culturally nuanced language (idioms, puns, holidays, and culturally embedded concepts) on an ordinal 0-3 quality scale; segment ratings additionally included an NA option for untranslated segments. Across full-text evaluations, mean overall quality is modest (1.68/3): GPT-5 (2.10/3), Claude Sonnet 4 (1.97/3), and Mistral Medium 3.1 (1.84/3) form the strongest tier with fewer catastrophic failures. Segment-level results show sharp category effects: holidays (2.20/3) and cultural concepts (2.19/3) translate notably better than idioms (1.65/3) and puns (1.45/3), and idioms are most likely to be left untranslated. Inter-rater reliability was assessed using Krippendorff's α and Gwet's AC2, indicating moderate agreement overall (Krippendorff's α = 0.45) with the lowest agreement for puns. These findings demonstrate a persistent gap between grammatical adequacy and cultural resonance. To our knowledge, this is the first multilingual, human-annotated benchmark focused explicitly on cultural nuance in translation and localisation. The results highlight the need for culturally informed training data, improved cross-lingual pragmatics, and evaluation frameworks that support systematic benchmarking of culturally grounded translation. |
| title | "Be My Cheese?": Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.04729 |