CARTE: A Benchmark for Mapping Language Model Knowledge Across France

• URL: http://arxiv.org/abs/2606.01995v1
• Date: Mon, 01 Jun 2026 09:50:50 GMT
• Title: CARTE: A Benchmark for Mapping Language Model Knowledge Across France
• Abstract summary: CARTE 1 is a benchmark for evaluating the ability of large language models to perform fine-grained reasoning over geographically grounded and regionally differentiated knowledge within France.<n>We introduce CARTE-LV, a subset targeting Linguistic Variation across French regions, enabling focused evaluation of language-related differences.<n>Our experiments reveal performance disparities across regions and model scales, suggesting systematic gaps in pretraining coverage and limited robustness to intra-national variation.
• Score: 19.651011443594196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models [51.61416200800499]
  GaoYao is a comprehensive benchmark with 182.3k samples, 26 languages and 51 nations/areas.<n>First, GaoYao proposes a unified framework categorizing evaluation tasks into three cultural layers.<n>Second, we achieve native-quality expansion by leveraging experts to rigorously localize subjective benchmarks into 19 languages.<n>Third, we conduct an in-depth diagnostic analysis on 20+ flagship and compact LLMs.
  arXiv  Detail & Related papers  (2026-04-22T06:19:46Z)
• AmharicStoryQA: A Multicultural Story Question Answering Benchmark in Amharic [25.361090310093072]
  We argue that evaluations overlook meaningful cultural variation that exists within a single language.<n>We introduce textbftextitAmharicStoryQA, a benchmark grounded in culturally diverse narratives from Amharic-speaking regions.
  arXiv  Detail & Related papers  (2026-02-02T20:28:19Z)
• MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation [91.22008265721952]
  MMA-ASIA centers on a human-curated, multilingual, and multimodally aligned benchmark covering 8 Asian countries and 10 languages.<n>This is the first dataset aligned at the input level across three modalities: text, image (visual question answering), and speech.<n>We propose a five-dimensional evaluation protocol that measures: (i) cultural-awareness disparities across countries, (ii) cross-lingual consistency, (iii) cross-modal consistency, (iv) cultural knowledge generalization, and (v) grounding validity.
  arXiv  Detail & Related papers  (2025-10-07T14:12:12Z)
• COLE: a Comprehensive Benchmark for French Language Understanding Evaluation [0.0]
  COLE is a new benchmark composed of 23 diverse task covering a broad range of NLU capabilities.<n>We benchmark 94 large language models (LLM), providing an extensive analysis of the current state of French NLU.
  arXiv  Detail & Related papers  (2025-10-06T17:26:41Z)
• XLQA: A Benchmark for Locale-Aware Multilingual Open-Domain Question Answering [48.913480244527925]
  Large Language Models (LLMs) have shown significant progress in Open-domain question answering (ODQA)<n>Most evaluations focus on English and assume locale-invariant answers across languages.<n>We introduce XLQA, a novel benchmark explicitly designed for locale-sensitive multilingual ODQA.
  arXiv  Detail & Related papers  (2025-08-22T07:00:13Z)
• IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces [28.21857463550941]
  We introduce IndoCulture, aimed at understanding the influence of geographical factors on language model reasoning ability. We ask local people to manually develop a cultural context and plausible options, across a set of predefined topics. Open-weight Llama-3 is competitive with GPT-4, while other open-weight models struggle, with accuracies below 50%.
  arXiv  Detail & Related papers  (2024-04-02T11:32:58Z)
• Unveiling Linguistic Regions in Large Language Models [49.298360366468934]
  Large Language Models (LLMs) have demonstrated considerable cross-lingual alignment and generalization ability. This paper conducts several investigations on the linguistic competence of LLMs.
  arXiv  Detail & Related papers  (2024-02-22T16:56:13Z)
• LLaMA Beyond English: An Empirical Study on Language Capability Transfer [49.298360366468934]
  We focus on how to effectively transfer the capabilities of language generation and following instructions to a non-English language. We analyze the impact of key factors such as vocabulary extension, further pretraining, and instruction tuning on transfer. We employ four widely used standardized testing benchmarks: C-Eval, MMLU, AGI-Eval, and GAOKAO-Bench.
  arXiv  Detail & Related papers  (2024-01-02T06:29:02Z)
• Quantifying the Dialect Gap and its Correlates Across Languages [69.18461982439031]
  This work will lay the foundation for furthering the field of dialectal NLP by laying out evident disparities and identifying possible pathways for addressing them through mindful data collection.
  arXiv  Detail & Related papers  (2023-10-23T17:42:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.