Automatic detection of hate and abusive language is essential to combat its online spread. Moreover, recognising and explaining hate speech serves to educate people about its negative effects. However, most current detection models operate as black boxes, lacking interpretability and explainability. In this context, Large Language Models (LLMs) have proven effective for hate speech detection and to promote interpretability. Nevertheless, they are computationally costly to run. In this work, we propose distilling big language models by using Chain-of-Thought to extract explanations that support the hate speech classification task. Having small language models for these tasks will contribute to their use in operational settings. In this paper, we demonstrate that distilled models deliver explanations of the same quality as larger models while surpassing them in classification performance. This dual capability, classifying and explaining, advances hate speech detection making it more affordable, understandable and actionable.
In a hate speech detection model, we should consider two critical aspects in addition to detection performance-bias and explainability. Hate speech cannot be identified based solely on the presence of specific words: the model should be able to reason like humans and be explainable. To improve the performance concerning the two aspects, we propose Masked Rationale Prediction (MRP) as an intermediate task. MRP is a task to predict the masked human rationales-snippets of a sentence that are grounds for human judgment-by referring to surrounding tokens combined with their unmasked rationales. As …
X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and A Novel LLM-consulted Explanation Framework
Indian Institute of Technology Indore（印度理工学院Indore）；Indian Institute of Information Technology Dharwad（印度信息科技学院Dharwad）；Arizona State University（亚利桑那州立大学）；Indian Institute of Technology Mandi（印度理工学院Mandi）
Indian Institute of Technology, Kharagpur（印度理工学院卡拉格普尔分校）
Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of hate speech. In this paper, we introduce HateXplain, the first benchmark hate speech dataset covering multiple aspects of the issue. Each post in our dataset is annotated from three different perspectives: the basic, commonly used 3-class classification (i.e., hate, offensive or normal), the target community (i.e., the community that has been the victim of hate speech/offensive s…
Boosting Accuracy and Interpretability in Multilingual Hate Speech Detection Through Layer Freezing and Explainable AI
Department of Computer Science（计算机科学系）；University of South Carolina（南卡罗来纳大学）；Department of Civil, Environmental, and Ocean Engineering（土木、环境与海洋工程系）；Stevens Institute of Technology（史蒂文斯理工学院）；School of Computing（计算学院）；University of Nebraska–Lincoln（内布拉斯加大学林肯分校）；Bowling Green State University（鲍灵格林州立大学）
Fraunhofer FIT（弗劳恩霍夫应用信息技术研究所）；RWTH Aachen University（亚琛工业大学）；Noakhali Science and Technology University（诺亚克利科技大学）；Begum Rokeya University（贝古姆·罗凯亚大学）；The University of Alabama（阿拉巴马大学）；National University of Ireland, Galway（爱尔兰国立高威大学）；Islamic University of Technology（伊斯兰科技大学）
The exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices, but also enables people to express anti-social behaviour like online harassment, cyberbullying, and hate speech. Numerous works have been proposed to utilize textual data for social and anti-social behaviour analysis, by predicting the contexts mostly for highly-resourced languages like English. However, some languages are under-resourced, e.g., South Asian languages like Bengali, that lack computational resources for accurate natural language…
Hate Speech takes many forms to target communities with derogatory comments, and takes humanity a step back in societal progress. HateXplain is a recently published and first dataset to use annotated spans in the form of rationales, along with speech classification categories and targeted communities to make the classification more humanlike, explainable, accurate and less biased. We tune BERT to perform this task in the form of rationales and class prediction, and compare our performance on different metrics spanning across accuracy, explainability and bias. Our novelty is threefold. Firstly,…
We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection. Although feature attribution models usually provide a single importance score for each token, we instead provide two complementary and theoretically-grounded scores -- necessity and sufficiency -- resulting in more informative explanations. We propose a transparent method that calculates these values by generating explicit perturbations of the input text, allowing the importance scores themselves to be explainable. We employ our method to explain the prediction…
Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning
Center for Precision Psychiatry, Mass General Hospital Department of Psychiatry, Harvard Medical School（精准精神病学中心，麻省总医院精神病科，哈佛医学院）；D-Lab University of California, Berkeley（加州大学伯克利分校D实验室）
The rise of hate speech on online platforms has led to an urgent need for effective content moderation. However, the subjective and multi-faceted nature of hateful online content, including implicit hate speech, poses significant challenges to human moderators and content moderation systems. To address this issue, we developed ToxVis, a visually interactive and explainable tool for classifying hate speech into three categories: implicit, explicit, and non-hateful. We fine-tuned two transformer-based models using RoBERTa, XLNET, and GPT-3 and used deep learning interpretation techniques to prov…
Jilin University（吉林大学）；Hong Kong Baptist University（香港浸会大学）
Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances. However, they often tailor automated solutions on manual fact-checked reports, suffering from limited news coverage and debunking delays. When a piece of news has not yet been fact-checked or debunked, certain amounts of relevant raw reports are usually disseminated on various media outlets, containing the wisdom of crowds to verify the news claim and explain its verdict. In this paper, we propose a novel Coarse-to-fine Cascaded Evidence-Di…
We conduct relatively extensive investigations of automatic hate speech (HS) detection using different state-of-the-art (SoTA) baselines over 11 subtasks of 6 different datasets. Our motivation is to determine which of the recent SoTA models is best for automatic hate speech detection and what advantage methods like data augmentation and ensemble may have on the best model, if any. We carry out 6 cross-task investigations. We achieve new SoTA on two subtasks - macro F1 scores of 91.73% and 53.21% for subtasks A and B of the HASOC 2020 dataset, where previous SoTA are 51.52% and 26.52%, respect…
We investigate the performance of a state-of-the art (SoTA) architecture T5 (available on the SuperGLUE) and compare with it 3 other previous SoTA architectures across 5 different tasks from 2 relatively diverse datasets. The datasets are diverse in terms of the number and types of tasks they have. To improve performance, we augment the training data by using an autoregressive model. We achieve near-SoTA results on a couple of the tasks - macro F1 scores of 81.66% for task A of the OLID 2019 dataset and 82.54% for task A of the hate speech and offensive content (HASOC) 2021 dataset, where SoTA…
HateMirage: An Explainable Multi-Dimensional Dataset for Decoding Faux Hate and Subtle Online Abuse
Indian Institute of Information Technology Dharwad（印度信息技术学院达尔瓦德）；Manipal Institute of Technology, Manipal Academy of Higher Education（曼普及高等教育学院技术学院）；Indraprastha Institute of Information Technology Delhi（印度普拉斯塔信息技术学院德里）
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Helmholtz Munich（亥姆霍兹慕尼黑中心）；Munich Data Science Institute (MDSI)（慕尼黑数据科学研究所）
HausaNLP at SemEval-2023 Task 10: Transfer Learning, Synthetic Data and Side-Information for Multi-Level Sexism Classification
Universiti Teknologi PETRONAS（马来西亚石油科技大学）；Bayero University, Kano（卡诺贝罗大学）；Ahmad Bello University, Zaria（扎里亚艾哈迈德·贝洛大学）；Kaduna State University（卡杜纳州立大学）；HausaNLP（豪萨语自然语言处理研究组）
AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages
University of Toronto（多伦多大学）；Mila - Quebec AI Institute, McGill University（魁北克AI研究院，麦吉尔大学）；Saarland University, Saarland Informatic Campus（萨尔兰大学，萨尔兰信息学院）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）
