This paper provides an overview of the UrduFake@FIRE2021 shared task, which focused on fake news detection in the Urdu language. The task involved binary classification of news articles into real or fake categories using a dataset of 1300 training and 300 testing articles across five domains. 34 teams registered, with 18 submitting results and 11 providing technical reports detailing various approaches from BoW to Transformer models, with the best system achieving an F1-macro score of 0.679.
The AraFinNLP 2024 shared task introduced two subtasks focused on Arabic financial NLP: multi-dialect intent detection and cross-dialect translation with intent preservation. It utilized the updated ArBanking77 dataset, containing 39k parallel queries in MSA and four dialects, labeled with 77 banking-related intents. 45 teams registered, with 11 participating in intent detection (achieving a top F1 score of 0.8773) and only 1 team attempting translation (achieving a BLEU score of 1.667). Why it matters: This initiative addresses the need for specialized Arabic NLP tools in the growing Arab financial sector, promoting advancements in areas like banking chatbots and machine translation.
The UrduFake@FIRE2021 shared task focused on fake news detection in the Urdu language, framed as a binary classification problem. 34 teams registered, with 18 submitting results and 11 providing technical reports, showcasing diverse approaches. The top-performing system utilized the stochastic gradient descent (SGD) algorithm, achieving an F-score of 0.679.
This paper introduces two shared tasks for abusive and threatening language detection in Urdu, a low-resource language with over 170 million speakers. The tasks involve binary classification of Urdu tweets into Abusive/Non-Abusive and Threatening/Non-Threatening categories, respectively. Datasets of 2400/6000 training tweets and 1100/3950 testing tweets were created and manually annotated, along with logistic regression and BERT-based baselines. 21 teams participated and the best systems achieved F1-scores of 0.880 and 0.545 on the abusive and threatening language tasks, respectively, with m-BERT showing the best performance.
The GenAI Content Detection Task 1 is a shared task on detecting machine-generated text, featuring monolingual (English) and multilingual subtasks. The task, part of the GenAI workshop at COLING 2025, attracted 36 teams for the English subtask and 26 for the multilingual one. The organizers provide a detailed overview of the data, results, system rankings, and analysis of the submitted systems.
Sai Praneeth Karimireddy from UC Berkeley presented a talk on building planetary-scale collaborative intelligence, highlighting the challenges of using distributed data in machine learning due to data silos and ethical-legal restrictions. He proposed collaborative systems like federated learning as a solution to bring together distributed data while respecting privacy. The talk addressed the need for efficiency, reliability, and management of divergent goals in these systems, suggesting the use of tools from optimization, statistics, and economics. Why it matters: Collaborative AI systems can unlock valuable distributed data in the region, especially in sensitive sectors like healthcare, while ensuring privacy and addressing ethical concerns.
This paper introduces ProgramFC, a fact-checking model that decomposes complex claims into simpler sub-tasks using a library of functions. The model uses LLMs to generate reasoning programs and executes them by delegating sub-tasks, enhancing explainability and data efficiency. Experiments on fact-checking datasets demonstrate ProgramFC's superior performance compared to baseline methods, with publicly available code and data.
The fifth Nuanced Arabic Dialect Identification (NADI) 2024 shared task aimed to advance Arabic NLP through dialect identification and dialect-to-MSA machine translation. 51 teams registered, with 12 participating and submitting 76 valid submissions across three subtasks. The winning teams achieved 50.57 F1 for multi-label dialect identification, 0.1403 RMSE for dialectness level identification, and 20.44 BLEU for dialect-to-MSA translation. Why it matters: The results highlight the continued challenges in Arabic dialect processing and provide a benchmark for future research in this area.