Saved in:
Bibliographic Details
Main Authors: Iranmanesh, Reihaneh, Davoudi, Saeedeh, Abrishamchian, Pasha, Frieder, Ophir, Goharian, Nazli
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.22827
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910053521424384
author Iranmanesh, Reihaneh
Davoudi, Saeedeh
Abrishamchian, Pasha
Frieder, Ophir
Goharian, Nazli
author_facet Iranmanesh, Reihaneh
Davoudi, Saeedeh
Abrishamchian, Pasha
Frieder, Ophir
Goharian, Nazli
contents 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 across three culturally grounded Persian datasets, 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. Our human evaluation further confirms that the proposed semantic similarity metric achieves higher agreement with human judgments than LLM-based judges. 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_22827
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models
Iranmanesh, Reihaneh
Davoudi, Saeedeh
Abrishamchian, Pasha
Frieder, Ophir
Goharian, Nazli
Computation and Language
Machine Learning
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 across three culturally grounded Persian datasets, 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. Our human evaluation further confirms that the proposed semantic similarity metric achieves higher agreement with human judgments than LLM-based judges. 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.
title TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Models
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2602.22827