paper-with-me

Papers

ELAB: Extensive LLM Alignment Benchmark in Persian Language

2025-04-17 · Zahra Pourbahman, Fatemeh Rajabi, Mohammadhossein Sadeghi, Omid Ghahroodi, Somaye Bakhshaei, Arash Amini, Reza Kazemi, Mahdieh Soleymani Baghshah

This paper presents a comprehensive evaluation framework for aligning Persian Large Language Models (LLMs) with critical ethical dimensions, including safety, fairness, and social norms. It addresses the gaps in existing LLM evaluation frameworks by adapting them to Persian linguistic and cultural contexts. This benchmark creates three types of Persian-language benchmarks: (i) translated data, (ii) new data generated synthetically, and (iii) new naturally collected data. We translate Anthropic Red Teaming data, AdvBench, HarmBench, and DecodingTrust into Persian. Furthermore, we create ProhibiBench-fa, SafeBench-fa, FairBench-fa, and SocialBench-fa as new datasets to address harmful and prohibited content in indigenous culture. Moreover, we collect extensive dataset as GuardBench-fa to consider Persian cultural norms. By combining these datasets, our work establishes a unified framework for evaluating Persian LLMs, offering a new approach to culturally grounded alignment evaluation. A systematic evaluation of Persian LLMs is performed across the three alignment aspects: safety (avoiding harmful content), fairness (mitigating biases), and social norms (adhering to culturally accepted behaviors). We present a publicly available leaderboard that benchmarks Persian LLMs with respect to safety, fairness, and social norms at: https://huggingface.co/spaces/MCILAB/LLM_Alignment_Evaluation.

📄 PDF Abstract BibTeX arXiv:2504.12553

Code (0)

등록된 구현이 없습니다.

Tasks

FairnessRed Teaming

Similar Papers 제목 키워드 기반

EPT Benchmark: Evaluation of Persian Trustworthiness in Large Language Models

2025-09-08 · Mohammad Reza Mirbagheri, Mohammad Mahdi Mirkamali, Zahra Motoshaker Arani, Ali Javeri 외 arxiv

Large Language Models (LLMs), trained on extensive datasets using advanced deep learning architectures, have demonstrated remarkable performance across a wide range of language tasks, becoming a cornerstone of modern AI …

MELAC: Massive Evaluation of Large Language Models with Alignment of Culture in Persian Language

2025-08-01 · Farhan Farsi, Farnaz Aghababaloo, Shahriar Shariati Motlagh, Parsa Ghofrani 외 arxiv

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 L…

PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models

2025-10-22 · Farhan Farsi, Shayan Bali, Fatemeh Valeh, Parsa Ghofrani 외 arxiv

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…

Bias Detection

FarsEval-PKBETS: A new diverse benchmark for evaluating Persian large language models

2025-04-20 · Mehrnoush Shamsfard, Zahra Saaberi, Mostafa Karimi manesh, Seyed Mohammad Hossein Hashemi 외

Research on evaluating and analyzing large language models (LLMs) has been extensive for resource-rich languages such as English, yet their performance in languages such as Persian has received considerably less attentio…

DescriptiveEthicsMultiple-choiceText Generation

Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation

2024-12-17 · Samin Mahdizadeh Sani, Pouya Sadeghi, Thuy-Trang Vu, Yadollah Yaghoobzadeh 외

Large language models (LLMs) have made great progress in classification and text generation tasks. However, they are mainly trained on English data and often struggle with low-resource languages. In this study, we explor…

Classificationparameter-efficient fine-tuningText GenerationTransfer Learning