@inproceedings{zinvandi-etal-2025-famteb,
title = "{F}a{MTEB}: Massive Text Embedding Benchmark in {P}ersian Language",
author = "Zinvandi, Erfan and
Alikhani, Morteza and
Sarmadi, Mehran and
Pourbahman, Zahra and
Arvin, Sepehr and
Kazemi, Reza and
Amini, Arash",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.614/",
doi = "10.18653/v1/2025.findings-emnlp.614",
pages = "11441--11468",
ISBN = "979-8-89176-335-7",
abstract = "In this paper, we introduce a comprehensive benchmark for Persian (Farsi) text embeddings, built upon the Massive Text Embedding Benchmark (MTEB). Our benchmark includes 63 datasets spanning seven different tasks: classification, clustering, pair classification, reranking, retrieval, summary retrieval, and semantic textual similarity. The datasets are a combination of existing, translated, and newly generated (synthetic) data, offering a diverse and robust evaluation framework for Persian language models. All newly translated and synthetic datasets were rigorously evaluated by both humans and automated systems to ensure high quality and reliability. Given the growing adoption of text embedding models in chatbots, evaluation datasets are becoming an essential component of chatbot development and Retrieval-Augmented Generation (RAG) systems. As a contribution, we include chatbot evaluation datasets in the MTEB benchmark for the first time. Additionally, we introduce the novel task of summary retrieval, which is not included in the standard MTEB tasks. Another key contribution of this work is the introduction of a substantial number of new Persian-language NLP datasets for both training and evaluation, many of which have no existing counterparts in Persian. We evaluate the performance of several Persian and multilingual embedding models across a wide range of tasks. This work presents an open-source benchmark with datasets, accompanying code, and a public leaderboard."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zinvandi-etal-2025-famteb">
<titleInfo>
<title>FaMTEB: Massive Text Embedding Benchmark in Persian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erfan</namePart>
<namePart type="family">Zinvandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morteza</namePart>
<namePart type="family">Alikhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehran</namePart>
<namePart type="family">Sarmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zahra</namePart>
<namePart type="family">Pourbahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sepehr</namePart>
<namePart type="family">Arvin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Kazemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Amini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>In this paper, we introduce a comprehensive benchmark for Persian (Farsi) text embeddings, built upon the Massive Text Embedding Benchmark (MTEB). Our benchmark includes 63 datasets spanning seven different tasks: classification, clustering, pair classification, reranking, retrieval, summary retrieval, and semantic textual similarity. The datasets are a combination of existing, translated, and newly generated (synthetic) data, offering a diverse and robust evaluation framework for Persian language models. All newly translated and synthetic datasets were rigorously evaluated by both humans and automated systems to ensure high quality and reliability. Given the growing adoption of text embedding models in chatbots, evaluation datasets are becoming an essential component of chatbot development and Retrieval-Augmented Generation (RAG) systems. As a contribution, we include chatbot evaluation datasets in the MTEB benchmark for the first time. Additionally, we introduce the novel task of summary retrieval, which is not included in the standard MTEB tasks. Another key contribution of this work is the introduction of a substantial number of new Persian-language NLP datasets for both training and evaluation, many of which have no existing counterparts in Persian. We evaluate the performance of several Persian and multilingual embedding models across a wide range of tasks. This work presents an open-source benchmark with datasets, accompanying code, and a public leaderboard.</abstract>
<identifier type="citekey">zinvandi-etal-2025-famteb</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.614</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.614/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>11441</start>
<end>11468</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FaMTEB: Massive Text Embedding Benchmark in Persian Language
%A Zinvandi, Erfan
%A Alikhani, Morteza
%A Sarmadi, Mehran
%A Pourbahman, Zahra
%A Arvin, Sepehr
%A Kazemi, Reza
%A Amini, Arash
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F zinvandi-etal-2025-famteb
%X In this paper, we introduce a comprehensive benchmark for Persian (Farsi) text embeddings, built upon the Massive Text Embedding Benchmark (MTEB). Our benchmark includes 63 datasets spanning seven different tasks: classification, clustering, pair classification, reranking, retrieval, summary retrieval, and semantic textual similarity. The datasets are a combination of existing, translated, and newly generated (synthetic) data, offering a diverse and robust evaluation framework for Persian language models. All newly translated and synthetic datasets were rigorously evaluated by both humans and automated systems to ensure high quality and reliability. Given the growing adoption of text embedding models in chatbots, evaluation datasets are becoming an essential component of chatbot development and Retrieval-Augmented Generation (RAG) systems. As a contribution, we include chatbot evaluation datasets in the MTEB benchmark for the first time. Additionally, we introduce the novel task of summary retrieval, which is not included in the standard MTEB tasks. Another key contribution of this work is the introduction of a substantial number of new Persian-language NLP datasets for both training and evaluation, many of which have no existing counterparts in Persian. We evaluate the performance of several Persian and multilingual embedding models across a wide range of tasks. This work presents an open-source benchmark with datasets, accompanying code, and a public leaderboard.
%R 10.18653/v1/2025.findings-emnlp.614
%U https://aclanthology.org/2025.findings-emnlp.614/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.614
%P 11441-11468
Markdown (Informal)
[FaMTEB: Massive Text Embedding Benchmark in Persian Language](https://aclanthology.org/2025.findings-emnlp.614/) (Zinvandi et al., Findings 2025)
ACL
- Erfan Zinvandi, Morteza Alikhani, Mehran Sarmadi, Zahra Pourbahman, Sepehr Arvin, Reza Kazemi, and Arash Amini. 2025. FaMTEB: Massive Text Embedding Benchmark in Persian Language. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 11441–11468, Suzhou, China. Association for Computational Linguistics.