With the increasing adoption of large language models (LLMs), ensuring their alignment with social norms has become a critical concern. While prior research has examined bias detection in various languages, there remains a significant gap in resources addressing social biases within Persian cultural contexts. In this work, we introduce PBBQ, a comprehensive benchmark dataset designed to evaluate social biases in Persian LLMs. Our benchmark, which encompasses 16 cultural categories, was developed through anonymous questionnaires completed by 250 diverse individuals across multiple demographics, in close collaboration with social science experts to ensure its validity. The resulting PBBQ dataset contains over 37,000 carefully curated questions, providing a foundation for the evaluation and mitigation of bias in Persian language models. We benchmark several open-source LLMs, a closed-source model, and Persian-specific fine-tuned models on PBBQ. Our findings reveal that current LLMs exhibit significant social biases across Persian culture. Additionally, by comparing model outputs to human responses, we observe that LLMs often replicate human bias patterns, highlighting the complex interplay between learned representations and cultural stereotypes. Our PBBQ dataset is also publicly available for use in future work. Content warning: This paper contains unsafe content.

Large Language Models (LLMs) are increasingly embedded in the daily lives of individuals across diverse social classes. This widespread integration raises urgent concerns about the subtle, implicit biases these models may contain. In this work, we investigate such biases through the lens of ethical reasoning, analyzing model responses to scenarios in a new dataset we propose comprising 1,016 scenarios, systematically categorized into ethical, unethical, and neutral types. Our study focuses on dimensions that are socially influential but less explored, including (i) residency status, (ii) political ideology, (iii) Fitness Status, (iv) educational attainment, and (v) attitudes toward AI. To assess LLMs’ behavior, we propose a baseline and employ one statistical test and one metric: a permutation test that reveals the presence of bias by comparing the probability distributions of ethical/unethical scenarios with the probability distribution of neutral scenarios on each demographic group, and a tendency measurement that captures the magnitude of bias with respect to the relative difference between probability distribution of ethical and unethical scenarios. Our evaluations of 12 prominent LLMs reveal persistent and nuanced biases across all four attributes, and Llama models exhibited the most pronounced biases. These findings highlight the need for refined ethical benchmarks and bias-mitigation tools in LLMs.

Hallucination is a persistent issue affecting all large language Models (LLMs), particularly within low-resource languages such as Persian. PerHalluEval (Persian Hallucination Evaluation) is the first dynamic hallucination evaluation benchmark tailored for the Persian language. Our benchmark leverages a three-stage LLM-driven pipeline, augmented with human validation, to generate plausible answers and summaries regarding QA and summarization tasks, focusing on detecting extrinsic and intrinsic hallucinations. Moreover, we used the log probabilities of generated tokens to select the most believable hallucinated instances. In addition, we engaged human annotators to highlight Persian-specific contexts in the QA dataset in order to evaluate LLMs’ performance on content specifically related to Persian culture. Our evaluation of 12 LLMs, including open- and closed-source models using PerHalluEval, revealed that the models generally struggle in detecting hallucinated Persian text. We showed that providing external knowledge, i.e., the original document for the summarization task, could mitigate hallucination partially. Furthermore, there was no significant difference in terms of hallucination when comparing LLMs specifically trained for Persian with others.

The Iranic language family includes many underrepresented languages and dialects that remain largely unexplored in modern NLP research. We introduce APARSIN, a multi-variety benchmark covering 14 Iranic languages, dialects, and accents, designed for sentiment analysis and machine translation. The dataset includes both high and low-resource varieties, several of which are endangered, capturing linguistic variation across them. We evaluate a set of instruction-tuned Large Language Models (LLMs) on these tasks and analyze their performance across the varieties. Our results highlight substantial performance gaps between standard Persian and other Iranic languages and dialects, demonstrating the need for more inclusive multilingual and dialectally diverse NLP benchmarks.

This study introduces a novel framework for evaluating Large Language Models (LLMs) and Vision-Language Models (VLMs) in Persian, a low-resource language. We develop comprehensive datasets to assess reasoning, linguistic understanding, and multimodal capabilities. Our datasets include Persian-OCR-QA for optical character recognition, Persian-VQA for visual question answering, Persian world-image puzzle for multimodal integration, Visual-Abstraction-Reasoning for abstract reasoning, and Iran-places for visual knowledge of Iranian figures and locations. We evaluate models like GPT-4o, Claude 3.5 Sonnet, and Llama 3.2 90B Vision, revealing their strengths and weaknesses in processing Persian. This research contributes to inclusive language processing by addressing the unique challenges of low-resource language evaluation.

As large language models (LLMs) become increasingly embedded in our daily lives, evaluating their quality and reliability across diverse contexts has become essential. While comprehensive benchmarks exist for assessing LLM performance in English, there remains a significant gap in evaluation resources for other languages. Moreover, because most LLMs are trained primarily on data rooted in European and American cultures, they often lack familiarity with non-Western cultural contexts. To address this limitation, our study focuses on the Persian language and Iranian culture. We introduce 19 new evaluation datasets specifically designed to assess LLMs on topics such as Iranian law, Persian grammar, Persian idioms, and university entrance exams. Using these datasets, we benchmarked 41 prominent LLMs, aiming to bridge the existing cultural and linguistic evaluation gap in the field. The evaluation results are publicly available on our live leaderboard: https://huggingface.co/spaces/opll-org/Open-Persian-LLM-Leaderboard

Nowadays, the usage of Large Language Models (LLMs) has increased, and LLMs have been used to generate texts in different languages and for different tasks. Additionally, due to the participation of remarkable companies such as Google and OpenAI, LLMs are now more accessible, and people can easily use them. However, an important issue is how we can detect AI-generated texts from human-written ones. In this article, we have investigated the problem of AI-generated text detection from two different aspects: semantics and syntax. Finally, we presented an AI model that can distinguish AI-generated texts from human-written ones with high accuracy on both multilingual and monolingual tasks using the M4 dataset. According to our results, using a semantic approach would be more helpful for detection. However, there is a lot of room for improvement in the syntactic approach, and it would be a good approach for future work.