TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models

• URL: http://arxiv.org/abs/2602.22827v1
• Date: Thu, 26 Feb 2026 10:08:02 GMT
• Title: TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models
• Abstract summary: This paper presents a comprehensive evaluation framework for assessing the cultural competence of large language models (LLMs) in Persian.<n>Our framework introduces a Persian-specific short-answer evaluation that combines rule-based morphological normalization with a hybrid syntactic and semantic similarity module.
• Score: 10.191206917633503
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents a comprehensive evaluation framework for assessing the cultural competence of large language models (LLMs) in Persian. Existing Persian cultural benchmarks rely predominantly on multiple-choice formats and English-centric metrics that fail to capture Persian's morphological complexity and semantic nuance. Our framework introduces a Persian-specific short-answer evaluation that combines rule-based morphological normalization with a hybrid syntactic and semantic similarity module, enabling robust soft-match scoring beyond exact string overlap. Through systematic evaluation of 15 state-of-the-art open- and closed-source models, we demonstrate that our hybrid evaluation improves scoring consistency by +10% compared to exact-match baselines by capturing meaning that surface-level methods cannot detect. We publicly release our evaluation framework, providing the first standardized benchmark for measuring cultural understanding in Persian and establishing a reproducible foundation for cross-cultural LLM evaluation research.

Related papers

• GhazalBench: Usage-Grounded Evaluation of LLMs on Persian Ghazals [5.695664084679044]
  We introduce GhazalBench, a benchmark for evaluating how large language models interact with Persian ghazals.<n>We observe a consistent dissociation: models generally capture poetic meaning but struggle with exact verse recall in completion-based settings.<n>Our findings highlight the need for evaluation frameworks that jointly assess meaning, form, and cue-dependent access to culturally significant texts.
  arXiv  Detail & Related papers  (2026-02-06T13:37:27Z)
• AQAScore: Evaluating Semantic Alignment in Text-to-Audio Generation via Audio Question Answering [97.52852990265136]
  We introduce AQAScore, a backbone-agnostic evaluation framework that leverages the reasoning capabilities of audio-aware large language models.<n>We evaluate AQAScore across multiple benchmarks, including human-rated relevance, pairwise comparison, and compositional reasoning tasks.
  arXiv  Detail & Related papers  (2026-01-21T07:35:36Z)
• On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation [88.77441715819366]
  Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content.<n>We propose a variety of likelihood- and generative-based evaluation methods that serve in place of naive global token perplexity.
  arXiv  Detail & Related papers  (2026-01-09T22:01:56Z)
• CURE: Cultural Understanding and Reasoning Evaluation - A Framework for "Thick" Culture Alignment Evaluation in LLMs [24.598338950728234]
  Large language models (LLMs) are increasingly deployed in culturally diverse environments.<n>Existing methods focus on de-contextualized correctness or forced-choice judgments.<n>We introduce a set of benchmarks that present models with realistic situational contexts.
  arXiv  Detail & Related papers  (2025-11-15T03:39:13Z)
• Evaluating Cultural Knowledge Processing in Large Language Models: A Cognitive Benchmarking Framework Integrating Retrieval-Augmented Generation [3.141716989847573]
  This study proposes a cognitive benchmarking framework to evaluate how large language models (LLMs) process and apply culturally specific knowledge.<n>The framework integrates Bloom's taxonomy with Retrieval-Augmented Generation (RAG) to assess model performance across six hierarchical cognitive domains.
  arXiv  Detail & Related papers  (2025-11-03T15:04:23Z)
• 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)
• Fùxì: A Benchmark for Evaluating Language Models on Ancient Chinese Text Understanding and Generation [20.87296508045343]
  We introduce Fuxi, a comprehensive benchmark that evaluates both understanding and generation capabilities across 21 diverse tasks.<n>We reveal significant performance gaps between understanding and generation tasks, with models achieving promising results in comprehension but struggling considerably in generation tasks.<n>Our findings highlight the current limitations in ancient Chinese text processing and provide insights for future model development.
  arXiv  Detail & Related papers  (2025-03-20T04:26:40Z)
• PerCul: A Story-Driven Cultural Evaluation of LLMs in Persian [19.816050739495573]
  PerCul is a dataset designed to assess the sensitivity of LLMs toward Persian culture.<n>PerCul features story-based, multiple-choice questions that capture culturally nuanced scenarios.<n>We evaluate several state-of-the-art multilingual and Persian-specific LLMs.
  arXiv  Detail & Related papers  (2025-02-11T11:07:44Z)
• Learning Evaluation Models from Large Language Models for Sequence Generation [61.8421748792555]
  We propose a three-stage evaluation model training method that utilizes large language models to generate labeled data for model-based metric development.<n> Experimental results on the SummEval benchmark demonstrate that CSEM can effectively train an evaluation model without human-labeled data.
  arXiv  Detail & Related papers  (2023-08-08T16:41:16Z)
• FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets [69.91340332545094]
  We introduce FLASK, a fine-grained evaluation protocol for both human-based and model-based evaluation. We experimentally observe that the fine-graininess of evaluation is crucial for attaining a holistic view of model performance.
  arXiv  Detail & Related papers  (2023-07-20T14:56:35Z)
• Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling [70.23876429382969]
  We propose a benchmark that can evaluate intra-sentence discourse properties across a diverse set of NLP tasks. Disco-Bench consists of 9 document-level testsets in the literature domain, which contain rich discourse phenomena. For linguistic analysis, we also design a diagnostic test suite that can examine whether the target models learn discourse knowledge.
  arXiv  Detail & Related papers  (2023-07-16T15:18:25Z)
• KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation [69.57018875757622]
  We propose KPEval, a comprehensive evaluation framework consisting of four critical aspects: reference agreement, faithfulness, diversity, and utility. Using KPEval, we re-evaluate 23 keyphrase systems and discover that established model comparison results have blind-spots.
  arXiv  Detail & Related papers  (2023-03-27T17:45:38Z)

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.