A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings

• URL: http://arxiv.org/abs/2505.12116v1
• Date: Sat, 17 May 2025 18:52:47 GMT
• Title: A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings
• Authors: Fitsum Gaim, Hoyun Song, Huije Lee, Changgeon Ko, Eui Jun Hwang, Jong C. Park,
• Abstract summary: This work presents a large-scale human-annotated benchmark dataset for abusive language detection in Tigrinya social media.<n>The dataset comprises 13,717 YouTube comments annotated by nine native speakers, collected from 7,373 videos with a total of over 1.2 billion views across 51 channels.<n>Our experiments reveal that small, specialized multi-task models outperform the current frontier models in the low-resource setting.
• Score: 8.361945776819528
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Content moderation research has recently made significant advances, but still fails to serve the majority of the world's languages due to the lack of resources, leaving millions of vulnerable users to online hostility. This work presents a large-scale human-annotated multi-task benchmark dataset for abusive language detection in Tigrinya social media with joint annotations for three tasks: abusiveness, sentiment, and topic classification. The dataset comprises 13,717 YouTube comments annotated by nine native speakers, collected from 7,373 videos with a total of over 1.2 billion views across 51 channels. We developed an iterative term clustering approach for effective data selection. Recognizing that around 64% of Tigrinya social media content uses Romanized transliterations rather than native Ge'ez script, our dataset accommodates both writing systems to reflect actual language use. We establish strong baselines across the tasks in the benchmark, while leaving significant challenges for future contributions. Our experiments reveal that small, specialized multi-task models outperform the current frontier models in the low-resource setting, achieving up to 86% accuracy (+7 points) in abusiveness detection. We make the resources publicly available to promote research on online safety.

Related papers

• Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data [59.30098850050971]
  Cross-lingual transfer learning can improve performance on tasks with limited labeled data.<n>We leverage nearest-neighbor retrieval to augment minimal labeled data in the target language.<n>We evaluate our approach on eight languages and demonstrate that it consistently outperforms models trained solely on the target language data.
  arXiv  Detail & Related papers  (2025-05-20T12:25:33Z)
• Entity-aware Cross-lingual Claim Detection for Automated Fact-checking [7.242609314791262]
  We introduce EX-Claim, an entity-aware cross-lingual claim detection model that generalizes well to handle claims written in any language.<n>Our proposed model significantly outperforms the baselines, across 27 languages, and achieves the highest rate of knowledge transfer, even with limited training data.
  arXiv  Detail & Related papers  (2025-03-19T14:00:55Z)
• Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon [78.12363425794214]
  We focus on zero-shot sentiment analysis tasks across 34 languages, including 6 high/medium-resource languages, 25 low-resource languages, and 3 code-switching datasets. We demonstrate that pretraining using multilingual lexicons, without using any sentence-level sentiment data, achieves superior zero-shot performance compared to models fine-tuned on English sentiment datasets.
  arXiv  Detail & Related papers  (2024-02-03T10:41:05Z)
• Hate Speech and Offensive Language Detection using an Emotion-aware Shared Encoder [1.8734449181723825]
  Existing works on hate speech and offensive language detection produce promising results based on pre-trained transformer models. This paper addresses a multi-task joint learning approach which combines external emotional features extracted from another corpora. Our findings demonstrate that emotional knowledge helps to more reliably identify hate speech and offensive language across datasets.
  arXiv  Detail & Related papers  (2023-02-17T09:31:06Z)
• Language Independent Stance Detection: Social Interaction-based Embeddings and Large Language Models [4.899818550820576]
  This paper aims to take on the stance detection task by placing the emphasis not so much on the text itself but on the interaction available on social networks.<n>We propose a new method to leverage social information such as friends retweets by generating Embeddings.<n>Our experiments on seven publicly available datasets and four different languages show that combining our relational embeddings with discriminative textual methods helps to substantially improve performance.
  arXiv  Detail & Related papers  (2022-10-11T18:13:43Z)
• No Language Left Behind: Scaling Human-Centered Machine Translation [69.28110770760506]
  We create datasets and models aimed at narrowing the performance gap between low and high-resource languages. We propose multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. Our model achieves an improvement of 44% BLEU relative to the previous state-of-the-art.
  arXiv  Detail & Related papers  (2022-07-11T07:33:36Z)
• IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages [87.5457337866383]
  We introduce the Image-Grounded Language Understanding Evaluation benchmark. IGLUE brings together visual question answering, cross-modal retrieval, grounded reasoning, and grounded entailment tasks across 20 diverse languages. We find that translate-test transfer is superior to zero-shot transfer and that few-shot learning is hard to harness for many tasks.
  arXiv  Detail & Related papers  (2022-01-27T18:53:22Z)
• Addressing the Challenges of Cross-Lingual Hate Speech Detection [115.1352779982269]
  In this paper we focus on cross-lingual transfer learning to support hate speech detection in low-resource languages. We leverage cross-lingual word embeddings to train our neural network systems on the source language and apply it to the target language. We investigate the issue of label imbalance of hate speech datasets, since the high ratio of non-hate examples compared to hate examples often leads to low model performance.
  arXiv  Detail & Related papers  (2022-01-15T20:48:14Z)
• Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models [86.02610674750345]
  Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks. We apply 14 adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations. All the language models and robust training methods we tested perform poorly on AdvGLUE, with scores lagging far behind the benign accuracy.
  arXiv  Detail & Related papers  (2021-11-04T12:59:55Z)
• Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training [32.800766653254634]
  We present the most comprehensive study of cross-lingual stance detection to date. We use 15 diverse datasets in 12 languages from 6 language families. For our experiments, we build on pattern-exploiting training, proposing the addition of a novel label encoder.
  arXiv  Detail & Related papers  (2021-09-13T15:20:06Z)
• Semi-automatic Generation of Multilingual Datasets for Stance Detection in Twitter [9.359018642178917]
  This paper presents a method to obtain multilingual datasets for stance detection in Twitter. We leverage user-based information to semi-automatically label large amounts of tweets.
  arXiv  Detail & Related papers  (2021-01-28T13:05:09Z)
• Learning to Learn Morphological Inflection for Resource-Poor Languages [105.11499402984482]
  We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines.
  arXiv  Detail & Related papers  (2020-04-28T05:13:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.