Benchmarking Frontier LLMs on Arabic Cultural and Sociolinguistic Knowledge: A Cross-Evaluation Framework with Human SME Ground Truth

• URL: http://arxiv.org/abs/2607.00139v1
• Date: Tue, 30 Jun 2026 20:18:32 GMT
• Title: Benchmarking Frontier LLMs on Arabic Cultural and Sociolinguistic Knowledge: A Cross-Evaluation Framework with Human SME Ground Truth
• Abstract summary: Cross-evaluation framework instantiated on two underrepresented Arabic dialect communities: Egyptian and Iraqi Arabic.<n>We contribute 103 validated prompt-rubric pairs authored and graded by native-speaker SMEs.<n>Across 1,307 judge evaluations: GPT-5.4 is the most reliable judge (MADj = 10.21 pp, Signed Error = -1.12%); four of five judges show systematic leniency (+2.01% to +6.56%)
• Score: 0.34797121357690153
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The cost of human expert evaluation is a principal bottleneck to deploying language models in specialized, high-stakes domains. This is particularly acute for Arabic sociolinguistic knowledge: credible grading requires not only linguistic fluency but deep cultural familiarity that cannot be approximated by surface-level metrics. We address this with a cross-evaluation framework instantiated on two underrepresented Arabic dialect communities: Egyptian and Iraqi Arabic. We contribute 103 validated prompt-rubric pairs (70 Egyptian, 33 Iraqi; 53 Cultural, 50 Linguistic), authored and graded by native-speaker SMEs using penalty-weighted rubrics distinguishing positive content requirements from answer-specific negative error criteria. Three frontier LLMs serve as target models (graded by human SMEs across 302 unique prompt-response pairs), while five frontier LLMs serve as automated judges enforcing a provider-level self-evaluation guard. A dual-metric scheme combining Mean Absolute Deviation (MAD) with Signed Mean Error separates directional grading bias from symmetric noise. Across 1,307 judge evaluations: GPT-5.4 is the most reliable judge (MADj = 10.21 pp, Signed Error = -1.12%); four of five judges show systematic leniency (+2.01% to +6.56%); Cultural tasks are harder to grade than Linguistic tasks for all judges (MAD gap 1.83-4.78 pp); and models substantially outperform on Egyptian prompts compared to Iraqi prompts. However, given leniency differences between Iraqi and Egyptian SMEs, we cannot solely attribute this gap to model knowledge. We therefore emphasize findings that do not assume identical leniency across human graders. Across all samples, implicit cultural reasoning -- requiring models to simulate native-speaker judgment rather than rely on lexical verification -- emerges as the primary failure mode for automated grading across all judge models.

Related papers

• Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Competence in Large Language Models [0.37331950863394864]
  We present a rubric-based benchmark for the Saudi dialect.<n>We catalogue 466 error instances under a nine-category taxonomy.<n>We observe a consistency-versus-ceiling trade-off and model-distinctive error signatures.
  arXiv  Detail & Related papers  (2026-08-30T19:31:35Z)
• Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality? [74.69723255239663]
  Grounded Personality Reasoning requires MLLMs to anchor each Big Five rating in observable evidence through a chain of rating, reasoning, and grounding.<n> MM-OCEAN is produced by a multi-agent pipeline with human verification, with timestamped behavioral observations, evidence-grounded trait analyses, and seven categories of cue-grounding MCQs.<n>The analysis uncovers a striking Prejudice Gap: across the field, 51% of correct ratings are not grounded in retrieved cues, and the Holistic-Grounding Rate spans only 0-33.5%.
  arXiv  Detail & Related papers  (2026-05-21T07:42:47Z)
• 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)
• When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models [6.821769033209393]
  "Cultural Ghosting" is the systematic erasure of linguistic markers unique to non-native English varieties during text processing.<n>We quantify this phenomenon using two novel metrics: Identity Erasure Rate (IER) & Semantic Preservation Score (SPS)<n>Our experiments demonstrate that explicit cultural-preservation prompts reduce erasure by 29% without sacrificing semantic quality.
  arXiv  Detail & Related papers  (2026-02-25T17:54:42Z)
• ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning [0.0]
  ALPS (Arabic Linguistic & Pragmatic Suite) is a native, expert-curated diagnostic challenge set probing Deep Semantics and Pragmatics.<n> ALPS targets the depth of linguistic understanding through 531 rigorously crafted questions across 15 tasks and 47 subtasks.<n>We developed the dataset with deep expertise in Arabic linguistics, guaranteeing cultural authenticity and eliminating translation artifacts.
  arXiv  Detail & Related papers  (2026-02-19T03:51:37Z)
• Mitigating Cultural Bias in LLMs via Multi-Agent Cultural Debate [7.517766226036547]
  Large language models (LLMs) exhibit systematic Western-centric bias, yet whether prompting in non-Western languages can mitigate this remains understudied.<n>We introduce CEBiasBench, a Chinese--English bilingual benchmark, and Multi-Agent Vote (MAV), which enables explicit no bias'' judgments.<n>Using this framework, we find that Chinese prompting merely shifts bias toward East Asian perspectives rather than eliminating it.
  arXiv  Detail & Related papers  (2026-01-17T16:00:34Z)
• Evaluating Large Language Models for Abstract Evaluation Tasks: An Empirical Study [1.412242138378466]
  Large language models (LLMs) can process requests and generate texts, but their feasibility for assessing academic content needs further investigation.<n>This study examined ChatGPT-5, Gemini-3-Pro, and Claude-Sonnet-4.5's consistency and reliability in evaluating abstracts compared to one another and to human reviewers.
  arXiv  Detail & Related papers  (2026-01-09T15:21:17Z)
• RefineBench: Evaluating Refinement Capability of Language Models via Checklists [71.02281792867531]
  We evaluate two refinement modes: guided refinement and self-refinement.<n>In guided refinement, both proprietary LMs and large open-weight LMs can leverage targeted feedback to refine responses to near-perfect levels within five turns.<n>These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses.
  arXiv  Detail & Related papers  (2025-11-27T07:20:52Z)
• DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models [54.10223256792762]
  We present DialectalArabicMMLU, a new benchmark for evaluating the performance of large language models (LLMs) across Arabic dialects.<n>We extend the MMLU-Redux framework through manual translation and adaptation of 3K multiple-choice question-answer pairs into five major dialects.
  arXiv  Detail & Related papers  (2025-10-31T15:17:06Z)
• I Am Aligned, But With Whom? MENA Values Benchmark for Evaluating Cultural Alignment and Multilingual Bias in LLMs [5.060243371992739]
  We introduce MENAValues, a novel benchmark designed to evaluate the cultural alignment and multilingual biases of large language models (LLMs)<n> Drawing from large-scale, authoritative human surveys, we curate a structured dataset that captures the sociocultural landscape of MENA with population-level response distributions from 16 countries.<n>Our analysis reveals three critical phenomena: "Cross-Lingual Value Shifts" where identical questions yield drastically different responses based on language, "Reasoning-Induced Degradation" where prompting models to explain their reasoning worsens cultural alignment, and "Logit Leakage" where models refuse sensitive questions while internal probabilities reveal strong hidden
  arXiv  Detail & Related papers  (2025-10-15T05:10:57Z)
• Which Cultural Lens Do Models Adopt? On Cultural Positioning Bias and Agentic Mitigation in LLMs [53.07843733899881]
  Large language models (LLMs) have unlocked a wide range of downstream generative applications.<n>We find that they also risk perpetuating subtle fairness issues tied to culture, positioning their generations from the perspectives of the mainstream US culture.<n>We propose 2 inference-time mitigation methods to resolve these biases.
  arXiv  Detail & Related papers  (2025-09-25T12:28:25Z)
• VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models [121.03333569013148]
  We introduce VisuLogic: a benchmark of 1,000 human-verified problems across six categories.<n>These types of questions can be evaluated to assess the visual reasoning capabilities of MLLMs from multiple perspectives.<n>Most models score below 30% accuracy-only slightly above the 25% random baseline and far below the 51.4% achieved by humans.
  arXiv  Detail & Related papers  (2025-04-21T17:59:53Z)
• Flames: Benchmarking Value Alignment of LLMs in Chinese [86.73527292670308]
  This paper proposes a value alignment benchmark named Flames. It encompasses both common harmlessness principles and a unique morality dimension that integrates specific Chinese values. Our findings indicate that all the evaluated LLMs demonstrate relatively poor performance on Flames.
  arXiv  Detail & Related papers  (2023-11-12T17:18:21Z)

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.