Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2606.01995 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914622796201984 |
|---|---|
| author | Carneiro, Sarah Almeida Xypolopoulos, Christos Fei, Xiao Zhang, Yang Vazirgiannis, Michalis |
| author_facet | Carneiro, Sarah Almeida Xypolopoulos, Christos Fei, Xiao Zhang, Yang Vazirgiannis, Michalis |
| contents | We introduce CARTE 1 (Culturally Anchored Regional-Territorial Evaluation), a multiplechoice benchmark for evaluating the ability of large language models (LLMs) to perform fine-grained reasoning over geographically grounded and regionally differentiated knowledge within France. While prior benchmarks focus on national-level cultural understanding, they largely overlook intra-country variation and the need to distinguish between closely related regional contexts. CARTE addresses this gap by introducing 2,431 questions spanning the 13 metropolitan regions of France and covering 14 thematic domains, including culture, language, demographics, economy, environment, and mobility. We further introduce CARTE-LV, a subset targeting Linguistic Variation across French regions, enabling focused evaluation of language-related differences. We evaluate 27 LLMs ranging from 1B to 12B parameters under few-shot settings. Our experiments reveal performance disparities across regions and model scales, suggesting systematic gaps in pretraining coverage and limited robustness to intra-national variation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01995 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CARTE: A Benchmark for Mapping Language Model Knowledge Across France Carneiro, Sarah Almeida Xypolopoulos, Christos Fei, Xiao Zhang, Yang Vazirgiannis, Michalis Computation and Language We introduce CARTE 1 (Culturally Anchored Regional-Territorial Evaluation), a multiplechoice benchmark for evaluating the ability of large language models (LLMs) to perform fine-grained reasoning over geographically grounded and regionally differentiated knowledge within France. While prior benchmarks focus on national-level cultural understanding, they largely overlook intra-country variation and the need to distinguish between closely related regional contexts. CARTE addresses this gap by introducing 2,431 questions spanning the 13 metropolitan regions of France and covering 14 thematic domains, including culture, language, demographics, economy, environment, and mobility. We further introduce CARTE-LV, a subset targeting Linguistic Variation across French regions, enabling focused evaluation of language-related differences. We evaluate 27 LLMs ranging from 1B to 12B parameters under few-shot settings. Our experiments reveal performance disparities across regions and model scales, suggesting systematic gaps in pretraining coverage and limited robustness to intra-national variation. |
| title | CARTE: A Benchmark for Mapping Language Model Knowledge Across France |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2606.01995 |