The use of propaganda has spiked on mainstream and social media, aiming to manipulate or mislead users. While efforts to automatically detect propaganda techniques in textual, visual, or multimodal content have increased, most of them primarily focus on English content. The majority of the recent initiatives targeting medium to low-resource languages produced relatively small annotated datasets, with a skewed distribution, posing challenges for the development of sophisticated propaganda detection models. To address this challenge, we carefully develop the largest propaganda dataset to date, ArPro, comprised of 8K paragraphs from newspaper articles, labeled at the text span level following a taxonomy of 23 propagandistic techniques. Furthermore, our work offers the first attempt to understand the performance of large language models (LLMs), using GPT-4, for fine-grained propaganda detection from text. Results showed that GPT-4’s performance degrades as the task moves from simply classifying a paragraph as propagandistic or not, to the fine-grained task of detecting propaganda techniques and their manifestation in text. Compared to models fine-tuned on the dataset for propaganda detection at different classification granularities, GPT-4 is still far behind. Finally, we evaluate GPT-4 on a dataset consisting of six other languages for span detection, and results suggest that the model struggles with the task across languages. We made the dataset publicly available for the community.

Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored to particular languages and tasks. LAraBench addresses this gap for Arabic Natural Language Processing (NLP) and Speech Processing tasks, including sequence tagging and content classification across different domains. We utilized models such as GPT-3.5-turbo, GPT-4, BLOOMZ, Jais-13b-chat, Whisper, and USM, employing zero and few-shot learning techniques to tackle 33 distinct tasks across 61 publicly available datasets. This involved 98 experimental setups, encompassing ~296K data points, ~46 hours of speech, and 30 sentences for Text-to-Speech (TTS). This effort resulted in 330+ sets of experiments. Our analysis focused on measuring the performance gap between SOTA models and LLMs. The overarching trend observed was that SOTA models generally outperformed LLMs in zero-shot learning, with a few exceptions. Notably, larger computational models with few-shot learning techniques managed to reduce these performance gaps. Our findings provide valuable insights into the applicability of LLMs for Arabic NLP and speech processing tasks.

The recent development and success of Large Language Models (LLMs) necessitate an evaluation of their performance across diverse NLP tasks in different languages. Although several frameworks have been developed and made publicly available, their customization capabilities for specific tasks and datasets are often complex for different users. In this study, we introduce the LLMeBench framework, which can be seamlessly customized to evaluate LLMs for any NLP task, regardless of language. The framework features generic dataset loaders, several model providers, and pre-implements most standard evaluation metrics. It supports in-context learning with zero- and few-shot settings. A specific dataset and task can be evaluated for a given LLM in less than 20 lines of code while allowing full flexibility to extend the framework for custom datasets, models, or tasks. The framework has been tested on 31 unique NLP tasks using 53 publicly available datasets within 90 experimental setups, involving approximately 296K data points. We open-sourced LLMeBench for the community (https://github.com/qcri/LLMeBench/) and a video demonstrating the framework is available online (https://youtu.be/9cC2m_abk3A).

The recent breakthroughs in Artificial Intelligence (AI) can be attributed to the remarkable performance of Large Language Models (LLMs) across a spectrum of research areas (e.g., machine translation, question-answering, automatic speech recognition, text-to-speech generation) and application domains (e.g., business, law, healthcare, education, and psychology). The success of these LLMs largely de- pends on specific training techniques, most notably instruction tuning, RLHF, and subsequent prompting to achieve the desired output. As the development of such LLMs continues to increase in both closed and open settings, evaluation has become crucial for understanding their generalization capabilities across different tasks, modalities, languages, and dialects. This evaluation process is tightly coupled with prompting, which plays a key role in obtain- ing better outputs. There has been attempts to evaluate such models focusing on diverse tasks, languages, and dialects, which suggests that the capabilities of LLMs are still limited to medium-to-low-resource languages due to the lack of representative datasets. The tutorial offers an overview of this emerging research area. We explore the capabilities of LLMs in terms of their performance, zero- and few-shot settings, fine-tuning, instructions tuning, and close vs. open models with a special emphasis on low-resource settings. In addition to LLMs for standard NLP tasks, we will focus on speech and multimodality.

Misinformation spreading in mainstream and social media has been misleading users in different ways. Manual detection and verification efforts by journalists and fact-checkers can no longer cope with the great scale and quick spread of misleading information. This motivated research and industry efforts to develop systems for analyzing and verifying news spreading online. The SemEval-2023 Task 3 is an attempt to address several subtasks under this overarching problem, targeting writing techniques used in news articles to affect readers’ opinions. The task addressed three subtasks with six languages, in addition to three “surprise” test languages, resulting in 27 different test setups. This paper describes our participating system to this task. Our team is one of the 6 teams that successfully submitted runs for all setups. The official results show that our system is ranked among the top 3 systems for 10 out of the 27 setups.

We present an overview of the ArAIEval shared task, organized as part of the first ArabicNLP 2023 conference co-located with EMNLP 2023. ArAIEval offers two tasks over Arabic text: (1) persuasion technique detection, focusing on identifying persuasion techniques in tweets and news articles, and (2) disinformation detection in binary and multiclass setups over tweets. A total of 20 teams participated in the final evaluation phase, with 14 and 16 teams participating in Task 1 and Task 2, respectively. Across both tasks, we observe that fine-tuning transformer models such as AraBERT is the core of majority of participating systems. We provide a description of the task setup, including description of datasets construction and the evaluation setup. We also provide a brief overview of the participating systems. All datasets and evaluation scripts from the shared task are released to the research community. We hope this will enable further research on such important tasks within the Arabic NLP community.

In this paper we introduce ArCOV19-Rumors, an Arabic COVID-19 Twitter dataset for misinformation detection composed of tweets containing claims from 27th January till the end of April 2020. We collected 138 verified claims, mostly from popular fact-checking websites, and identified 9.4K relevant tweets to those claims. Tweets were manually-annotated by veracity to support research on misinformation detection, which is one of the major problems faced during a pandemic. ArCOV19-Rumors supports two levels of misinformation detection over Twitter: verifying free-text claims (called claim-level verification) and verifying claims expressed in tweets (called tweet-level verification). Our dataset covers, in addition to health, claims related to other topical categories that were influenced by COVID-19, namely, social, politics, sports, entertainment, and religious. Moreover, we present benchmarking results for tweet-level verification on the dataset. We experimented with SOTA models of versatile approaches that either exploit content, user profiles features, temporal features and propagation structure of the conversational threads for tweet verification.

In this paper, we present ArCOV-19, an Arabic COVID-19 Twitter dataset that spans one year, covering the period from 27th of January 2020 till 31st of January 2021. ArCOV-19 is the first publicly-available Arabic Twitter dataset covering COVID-19 pandemic that includes about 2.7M tweets alongside the propagation networks of the most-popular subset of them (i.e., most-retweeted and -liked). The propagation networks include both retweetsand conversational threads (i.e., threads of replies). ArCOV-19 is designed to enable research under several domains including natural language processing, information retrieval, and social computing. Preliminary analysis shows that ArCOV-19 captures rising discussions associated with the first reported cases of the disease as they appeared in the Arab world. In addition to the source tweets and the propagation networks, we also release the search queries and the language-independent crawler used to collect the tweets to encourage the curation of similar datasets.

In this paper we describe our QU-BIGIR system for the Arabic subtask D of the SemEval 2017 Task 3. Our approach builds on our participation in the past version of the same subtask. This year, our system uses different similarity measures that encodes lexical and semantic pairwise similarity of text pairs. In addition to well known similarity measures such as cosine similarity, we use other measures based on the summary statistics of word embedding representation for a given text. To rank a list of candidate question answer pairs for a given question, we learn a linear SVM classifier over our similarity features. Our best resulting run came second in subtask D with a very competitive performance to the first-ranking system.