This is an evaluation harness for the HumanEval problem solving dataset described in the paper "Evaluating Large Language Models Trained on Code". It used to measure functional correctness for synthesizing programs from docstrings. It consists of 164 original programming problems, assessing language comprehension, algorithms, and simple mathematics, with some comparable to simple software interview questions.

930 PAPERS • 2 BENCHMARKS

The Universal Dependencies (UD) project seeks to develop cross-linguistically consistent treebank annotation of morphology and syntax for multiple languages. The first version of the dataset was released in 2015 and consisted of 10 treebanks over 10 languages. Version 2.7 released in 2020 consists of 183 treebanks over 104 languages. The annotation consists of UPOS (universal part-of-speech tags), XPOS (language-specific part-of-speech tags), Feats (universal morphological features), Lemmas, dependency heads and universal dependency labels.

515 PAPERS • 5 BENCHMARKS

Common Voice is an audio dataset that consists of a unique MP3 and corresponding text file. There are 9,283 recorded hours in the dataset. The dataset also includes demographic metadata like age, sex, and accent. The dataset consists of 7,335 validated hours in 60 languages.

408 PAPERS • 93 BENCHMARKS

The Cross-lingual Natural Language Inference (XNLI) corpus is the extension of the Multi-Genre NLI (MultiNLI) corpus to 15 languages. The dataset was created by manually translating the validation and test sets of MultiNLI into each of those 15 languages. The English training set was machine translated for all languages. The dataset is composed of 122k train, 2490 validation and 5010 test examples.

344 PAPERS • 9 BENCHMARKS

OntoNotes 5.0 is a large corpus comprising various genres of text (news, conversational telephone speech, weblogs, usenet newsgroups, broadcast, talk shows) in three languages (English, Chinese, and Arabic) with structural information (syntax and predicate argument structure) and shallow semantics (word sense linked to an ontology and coreference).

252 PAPERS • 12 BENCHMARKS

MuST-C currently represents the largest publicly available multilingual corpus (one-to-many) for speech translation. It covers eight language directions, from English to German, Spanish, French, Italian, Dutch, Portuguese, Romanian and Russian. The corpus consists of audio, transcriptions and translations of English TED talks, and it comes with a predefined training, validation and test split.

214 PAPERS • 2 BENCHMARKS

XQuAD (Cross-lingual Question Answering Dataset) is a benchmark dataset for evaluating cross-lingual question answering performance. The dataset consists of a subset of 240 paragraphs and 1190 question-answer pairs from the development set of SQuAD v1.1 (Rajpurkar et al., 2016) together with their professional translations into ten languages: Spanish, German, Greek, Russian, Turkish, Arabic, Vietnamese, Thai, Chinese, and Hindi. Consequently, the dataset is entirely parallel across 11 languages.

184 PAPERS • 1 BENCHMARK

MLQA (MultiLingual Question Answering) is a benchmark dataset for evaluating cross-lingual question answering performance. MLQA consists of over 5K extractive QA instances (12K in English) in SQuAD format in seven languages - English, Arabic, German, Spanish, Hindi, Vietnamese and Simplified Chinese. MLQA is highly parallel, with QA instances parallel between 4 different languages on average.

161 PAPERS • 1 BENCHMARK

This corpus comprises of monolingual data for 100+ languages and also includes data for romanized languages. This was constructed using the urls and paragraph indices provided by the CC-Net repository by processing January-December 2018 Commoncrawl snapshots. Each file comprises of documents separated by double-newlines and paragraphs within the same document separated by a newline. The data is generated using the open source CC-Net repository.

111 PAPERS • NO BENCHMARKS YET

FLoRes-200 doubles the existing language coverage of FLoRes-101. Given the nature of the new languages, which have less standardization and require more specialized professional translations, the verification process became more complex. This required modifications to the translation workflow. FLoRes-200 has several languages which were not translated from English. Specifically, several languages were translated from Spanish, French, Russian, and Modern Standard Arabic.

103 PAPERS • 1 BENCHMARK

WikiANN, also known as PAN-X, is a multilingual named entity recognition dataset. It consists of Wikipedia articles that have been annotated with LOC (location), PER (person), and ORG (organization) tags in the IOB2 format¹². This dataset serves as a valuable resource for training and evaluating named entity recognition models across various languages.

69 PAPERS • 3 BENCHMARKS

OSCAR or Open Super-large Crawled ALMAnaCH coRpus is a huge multilingual corpus obtained by language classification and filtering of the Common Crawl corpus using the goclassy architecture. The dataset used for training multilingual models such as BART incorporates 138 GB of text.

64 PAPERS • NO BENCHMARKS YET

End-to-end speech-to-text translation (ST) has recently witnessed an increased interest given its system simplicity, lower inference latency and less compounding errors compared to cascaded ST (i.e. speech recognition + machine translation). End-to-end ST model training, however, is often hampered by the lack of parallel data. Thus, we created CoVoST, a large-scale multilingual ST corpus based on Common Voice, to foster ST research with the largest ever open dataset. Its latest version covers translations from English into 15 languages---Arabic, Catalan, Welsh, German, Estonian, Persian, Indonesian, Japanese, Latvian, Mongolian, Slovenian, Swedish, Tamil, Turkish, Chinese---and from 21 languages into English, including the 15 target languages as well as Spanish, French, Italian, Dutch, Portuguese, Russian. It has total 2,880 hours of speech and is diversified with 78K speakers.

61 PAPERS • NO BENCHMARKS YET

XL-Sum is a comprehensive and diverse dataset for abstractive summarization comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public dataset is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by human and intrinsic evaluation.

60 PAPERS • NO BENCHMARKS YET

WikiLingua includes ~770k article and summary pairs in 18 languages from WikiHow. Gold-standard article-summary alignments across languages are extracted by aligning the images that are used to describe each how-to step in an article.

48 PAPERS • 5 BENCHMARKS

Multilingual Knowledge Questions and Answers (MKQA) is an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). The goal of this dataset is to provide a challenging benchmark for question answering quality across a wide set of languages. Answers are based on a language-independent data representation, making results comparable across languages and independent of language-specific passages. With 26 languages, this dataset supplies the widest range of languages to-date for evaluating question answering.

46 PAPERS • NO BENCHMARKS YET

AVSpeech is a large-scale audio-visual dataset comprising speech clips with no interfering background signals. The segments are of varying length, between 3 and 10 seconds long, and in each clip the only visible face in the video and audible sound in the soundtrack belong to a single speaking person. In total, the dataset contains roughly 4700 hours of video segments with approximately 150,000 distinct speakers, spanning a wide variety of people, languages and face poses.

40 PAPERS • NO BENCHMARKS YET

CoVoST is a large-scale multilingual speech-to-text translation corpus. Its latest 2nd version covers translations from 21 languages into English and from English into 15 languages. It has total 2880 hours of speech and is diversified with 78K speakers and 66 accents.

33 PAPERS • 1 BENCHMARK

Arabic Sentiment Tweets Dataset (ASTD) is an Arabic social sentiment analysis dataset gathered from Twitter. It consists of about 10,000 tweets which are classified as objective, subjective positive, subjective negative, and subjective mixed.

31 PAPERS • 1 BENCHMARK

The Image-Grounded Language Understanding Evaluation (IGLUE) benchmark brings together—by both aggregating pre-existing datasets and creating new ones—visual question answering, cross-modal retrieval, grounded reasoning, and grounded entailment tasks across 20 diverse languages. The benchmark enables the evaluation of multilingual multimodal models for transfer learning, not only in a zero-shot setting, but also in newly defined few-shot learning setups.

28 PAPERS • 13 BENCHMARKS

CVSS is a massively multilingual-to-English speech to speech translation (S2ST) corpus, covering sentence-level parallel S2ST pairs from 21 languages into English. CVSS is derived from the Common Voice speech corpus and the CoVoST 2 speech-to-text translation (ST) corpus, by synthesizing the translation text from CoVoST 2 into speech using state-of-the-art TTS systems

24 PAPERS • 4 BENCHMARKS

license: apache-2.0 tags: human-feedback size_categories: 100K<n<1M pretty_name: OpenAssistant Conversations

24 PAPERS • NO BENCHMARKS YET

XStoryCloze consists of the professionally translated version of the English StoryCloze dataset (Spring 2016 version) to 10 non-English languages. This dataset is intended to be used for evaluating the zero- and few-shot learning capabilities of multlingual language models. This dataset is released by Meta AI.

24 PAPERS • NO BENCHMARKS YET

XGLUE is an evaluation benchmark XGLUE,which is composed of 11 tasks that span 19 languages. For each task, the training data is only available in English. This means that to succeed at XGLUE, a model must have a strong zero-shot cross-lingual transfer capability to learn from the English data of a specific task and transfer what it learned to other languages. Comparing to its concurrent work XTREME, XGLUE has two characteristics: First, it includes cross-lingual NLU and cross-lingual NLG tasks at the same time; Second, besides including 5 existing cross-lingual tasks (i.e. NER, POS, MLQA, PAWS-X and XNLI), XGLUE selects 6 new tasks from Bing scenarios as well, including News Classification (NC), Query-Ad Matching (QADSM), Web Page Ranking (WPR), QA Matching (QAM), Question Generation (QG) and News Title Generation (NTG). Such diversities of languages, tasks and task origin provide a comprehensive benchmark for quantifying the quality of a pre-trained model on cross-lingual natural lan

22 PAPERS • 2 BENCHMARKS

iSarcasmEval is the first shared task to target intended sarcasm detection: the data for this task was provided and labelled by the authors of the texts themselves. Such an approach minimises the downfalls of other methods to collect sarcasm data, which rely on distant supervision or third-party annotations. The shared task contains two languages, English and Arabic, and three subtasks: sarcasm detection, sarcasm category classification, and pairwise sarcasm identification given a sarcastic sentence and its non-sarcastic rephrase. The task received submissions from 60 different teams, with the sarcasm detection task being the most popular. Most of the participating teams utilised pre-trained language models. In this paper, we provide an overview of the task, data, and participating teams.

22 PAPERS • NO BENCHMARKS YET

Extracted from the Tashkeela Corpus, the dataset consists of 55K lines containing about 2.3M words.

17 PAPERS • 1 BENCHMARK

LABR is a large sentiment analysis dataset to-date for the Arabic language. It consists of over 63,000 book reviews, each rated on a scale of 1 to 5 stars.

17 PAPERS • 1 BENCHMARK

MINTAKA is a complex, natural, and multilingual dataset designed for experimenting with end-to-end question-answering models. It is composed of 20,000 question-answer pairs collected in English, annotated with Wikidata entities, and translated into Arabic, French, German, Hindi, Italian, Japanese, Portuguese, and Spanish for a total of 180,000 samples. Mintaka includes 8 types of complex questions, including superlative, intersection, and multi-hop questions, which were naturally elicited from crowd workers.

17 PAPERS • NO BENCHMARKS YET

The first parallel corpus composed from United Nations documents published by the original data creator. The parallel corpus presented consists of manually translated UN documents from the last 25 years (1990 to 2014) for the six official UN languages, Arabic, Chinese, English, French, Russian, and Spanish.

17 PAPERS • NO BENCHMARKS YET

xSID, a new evaluation benchmark for cross-lingual (X) Slot and Intent Detection in 13 languages from 6 language families, including a very low-resource dialect, covering Arabic (ar), Chinese (zh), Danish (da), Dutch (nl), English (en), German (de), Indonesian (id), Italian (it), Japanese (ja), Kazakh (kk), Serbian (sr), Turkish (tr) and an Austro-Bavarian German dialect, South Tyrolean (de-st).

17 PAPERS • NO BENCHMARKS YET

OntoNotes Release 4.0 contains the content of earlier releases -- OntoNotes Release 1.0 LDC2007T21, OntoNotes Release 2.0 LDC2008T04 and OntoNotes Release 3.0 LDC2009T24 -- and adds newswire, broadcast news, broadcast conversation and web data in English and Chinese and newswire data in Arabic. This cumulative publication consists of 2.4 million words as follows: 300k words of Arabic newswire 250k words of Chinese newswire, 250k words of Chinese broadcast news, 150k words of Chinese broadcast conversation and 150k words of Chinese web text and 600k words of English newswire, 200k word of English broadcast news, 200k words of English broadcast conversation and 300k words of English web text.

16 PAPERS • 1 BENCHMARK

ArSarcasm-v2 is an extension of the original ArSarcasm dataset published along with the paper From Arabic Sentiment Analysis to Sarcasm Detection: The ArSarcasm Dataset. ArSarcasm-v2 conisists of ArSarcasm along with portions of DAICT corpus and some new tweets. Each tweet was annotated for sarcasm, sentiment and dialect. The final dataset consists of 15,548 tweets divided into 12,548 training tweets and 3,000 testing tweets. ArSarcasm-v2 was used and released as a part of the shared task on sarcasm detection and sentiment analysis in Arabic.

15 PAPERS • NO BENCHMARKS YET

ArSarcasm is a new Arabic sarcasm detection dataset. The dataset was created using previously available Arabic sentiment analysis datasets (SemEval 2017 and ASTD) and adds sarcasm and dialect labels to them. The dataset contains 10,547 tweets, 1,682 (16%) of which are sarcastic.

13 PAPERS • NO BENCHMARKS YET

X-FACT is a large publicly available multilingual dataset for factual verification of naturally existing real-world claims. The dataset contains short statements in 25 languages and is labeled for veracity by expert fact-checkers. The dataset includes a multilingual evaluation benchmark that measures both out-of-domain generalization, and zero-shot capabilities of the multilingual models.

13 PAPERS • 1 BENCHMARK

Synbols is a dataset generator designed for probing the behavior of learning algorithms. By defining the distribution over latent factors one can craft a dataset specifically tailored to answer specific questions about a given algorithm.

11 PAPERS • NO BENCHMARKS YET

Global Voices is a multilingual dataset for evaluating cross-lingual summarization methods. It is extracted from social-network descriptions of Global Voices news articles to cheaply collect evaluation data for into-English and from-English summarization in 15 languages.

9 PAPERS • NO BENCHMARKS YET

A large-scale corpus of Gulf Arabic consisting of 110 million words from 1,200 forum novels.

7 PAPERS • NO BENCHMARKS YET

ArCOV-19 is an Arabic COVID-19 Twitter dataset that covers the period from 27th of January till 30th of April 2020. ArCOV-19 is the first publicly-available Arabic Twitter dataset covering COVID-19 pandemic that includes over 1M tweets alongside the propagation networks of the most-popular subset of them (i.e., most-retweeted and -liked).

6 PAPERS • NO BENCHMARKS YET

The WikiNews Arabic Diacritization dataset is a test set composed of 70 WikiNews articles (majority are from 2013 and 2014) that cover a variety of themes, namely: politics, economics, health, science and technology, sports, arts, and culture. The articles are evenly distributed among the different themes (10 per theme). The articles contain 18,300 words with around 400 different sentences (Each line is considered as a sentence).

6 PAPERS • NO BENCHMARKS YET

MuMiN is a misinformation graph dataset containing rich social media data (tweets, replies, users, images, articles, hashtags), spanning 21 million tweets belonging to 26 thousand Twitter threads, each of which have been semantically linked to 13 thousand fact-checked claims across dozens of topics, events and domains, in 41 different languages, spanning more than a decade.

5 PAPERS • 3 BENCHMARKS

ArCOV19-Rumors is an Arabic COVID-19 Twitter dataset for misinformation detection composed of tweets containing claims from 27th January till the end of April 2020.

4 PAPERS • NO BENCHMARKS YET

CIDAR contains 10,000 instructions and their output. The dataset was created by selecting around 9,109 samples from Alpagasus dataset then translating it to Arabic using ChatGPT. In addition, we append that with around 891 Arabic grammar instructions from the webiste Ask the teacher. All the 10,000 samples were reviewed by around 12 reviewers.

4 PAPERS • NO BENCHMARKS YET

GeoCoV19 is a large-scale Twitter dataset containing more than 524 million multilingual tweets. The dataset contains around 378K geotagged tweets and 5.4 million tweets with Place information. The annotations include toponyms from the user location field and tweet content and resolve them to geolocations such as country, state, or city level. In this case, 297 million tweets are annotated with geolocation using the user location field and 452 million tweets using tweet content.

4 PAPERS • NO BENCHMARKS YET

The AROT-COV23 (ARabic Original Tweets on COVID-19 as of 2023) dataset is a large-scale collection of original Arabic tweets related to COVID-19, spanning from January 2020 to January 2023, and the period for which we collected the data runs from January 1, 2020 to January 5, 2023. The dataset contains approximately 500,000 original tweets, providing a rich source of information on how Arabic-speaking Twitter users have discussed and shared information about the pandemic. For more details on this dataset, please see the paper in the citation section below.

3 PAPERS • NO BENCHMARKS YET

A benchmark Arabic dataset for commonsense understanding and validation as well as a baseline research and models trained using the same dataset.

3 PAPERS • NO BENCHMARKS YET

The CATT benchmark dataset comprises 742 sentences, which were scraped from an internet news source in 2023. It covers multiple topics including science and technology, economics, politics, sports, arts, and culture. It was manually diacritized by two expert native Arabic speakers and then validated by a third expert. This dataset contains names of people and places in both Arabic and English. As for the English names, they are written in Arabic letters and diacritized based on their pronunciation. Also, the numbers in the sentences are written in textual form rather than the numeric form which helps in evaluating the models without the need for a text normalizer (TN).

3 PAPERS • 1 BENCHMARK

The DAWT dataset consists of Densely Annotated Wikipedia Texts across multiple languages. The annotations include labeled text mentions mapping to entities (represented by their Freebase machine ids) as well as the type of the entity. The data set contains total of 13.6M articles, 5.0B tokens, 13.8M mention entity co-occurrences. DAWT contains 4.8 times more anchor text to entity links than originally present in the Wikipedia markup. Moreover, it spans several languages including English, Spanish, Italian, German, French and Arabic.

3 PAPERS • NO BENCHMARKS YET

We introduce HumanEval-XL, a massively multilingual code generation benchmark specifically crafted to address this deficiency. HumanEval-XL establishes connections between 23 NLs and 12 programming languages (PLs), and comprises of a collection of 22,080 prompts with an average of 8.33 test cases. By ensuring parallel data across multiple NLs and PLs, HumanEval-XL offers a comprehensive evaluation platform for multilingual LLMs, allowing the assessment of the understanding of different NLs. Our work serves as a pioneering step towards filling the void in evaluating NL generalization in the area of multilingual code generation. We make our evaluation code and data publicly available at https://github.com/FloatAI/HumanEval-XL.

3 PAPERS • NO BENCHMARKS YET