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.

Recommender systems play an important role in e-commerce websites as they improve the customer journey by helping the users find what they want at the right moment. In this paper, we focus on identifying a complementary relationship between the products of an e-commerce company. We propose a content-based recommender system for detecting complementary products, using Siamese Neural Networks (SNN). To this end, we implement and compare two different models: Siamese Convolutional Neural Network (CNN) and Siamese Long Short-Term Memory (LSTM). Moreover, we propose an extension of the SNN approach to handling millions of products in a matter of seconds, and we reduce the training time complexity by half. In the experiments, we show that Siamese LSTM can predict complementary products with an accuracy of ~85% using only the product titles.