| Challenge: | Hate speech detection models are evaluated on a held-out test data, but they are incapable of identifying weaknesses. |
| Approach: | They propose to use multilingual hate speech detection models to evaluate their performance on social media conversation. |
| Outcome: | The proposed model can detect hate speech in multiple languages using a real-world conversation on social media. |
Similar Papers
HateCheck: Functional Tests for Hate Speech Detection Models (2021.acl-long)
Copied to clipboard
| Challenge: | Hate speech detection models are evaluated by measuring their performance on held-out test data using metrics such as accuracy and F1 score. |
| Approach: | They propose a suite of functional tests for hate speech detection models that measure model performance on held-out test data and then craft test cases to validate their quality. |
| Outcome: | The proposed tests show that the proposed models perform poorly on a small set of widely-used hate speech datasets. |
HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter (2025.acl-long)
Copied to clipboard
Manuel Tonneau, Diyi Liu, Niyati Malhotra, Scott A. Hale, Samuel Fraiberger, Victor Orozco-Olvera, Paul Röttger
| Challenge: | Prior work on automated hate speech detection models has been limited due to systematic biases in evaluation datasets and poor performance across geographies. |
| Approach: | They propose to construct a global hate speech dataset representative of social media settings from tweets posted on September 21, 2022. |
| Outcome: | The proposed dataset covers eight languages and four English-speaking countries and covers eight countries where English is the main language on Twitter. |
Multilingual and Multi-Aspect Hate Speech Analysis (D19-1)
Copied to clipboard
| Challenge: | Current research on hate speech analysis is oriented towards monolingual and single classification tasks. |
| Approach: | They propose to use a multilingual multi-aspect hate speech analysis dataset to test current methods . they evaluate the dataset in various classification settings and discuss how to leverage annotations . |
| Outcome: | The proposed dataset can be used to improve hate speech detection and classification in general. |
Evaluating ChatGPT against Functionality Tests for Hate Speech Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models like ChatGPT have shown a great promise in detecting hate speech, but they lack the capability to perform in a holistic fashion. |
| Approach: | They evaluate the ChatGPT model's strengths and weaknesses by performing functional tests across 11 languages to uncover their weaknesses. |
| Outcome: | The proposed model performs poorly across 11 languages and is based on functional tests. |
Hate Speech and Offensive Language Detection in Bengali (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing research on hate speech detection in English does not cover low-resource languages like Bengali. |
| Approach: | They develop an annotated dataset of 10K Bengali posts consisting of 5K actual and 5K Romanized Bengali tweets. |
| Outcome: | The proposed model outperforms other models on training actual and romanized datasets by interpreting the semantic expressions better. |
Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish (2025.findings-naacl)
Copied to clipboard
| Challenge: | Hate speech detection deals with many language variants, slang, nuances, and cultural nuances. |
| Approach: | They propose to use large language models to detect hate speech in Rioplatense Spanish . they compare their results to those of a state-of-the-art BERT classifier . |
| Outcome: | The proposed models show lower precision than the state-of-the-art classifier, but are sensitive to highly nuanced cases. |
GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection? (2024.lrec-main)
Copied to clipboard
| Challenge: | HateCheck test cases are generic and have simplistic sentence structures that do not match the real-world data. |
| Approach: | They propose a framework to generate more diverse and realistic functional tests from scratch by instructing large language models. |
| Outcome: | The proposed framework generates more diverse and realistic functional tests from scratch by instructing large language models (LLMs). |
Directions for NLP Practices Applied to Online Hate Speech Detection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to address hate speech in online spaces have relied on conventions and practices from NLP. |
| Approach: | They argue that many conventions in NLP are poorly suited for the problem and encourage researchers to develop methods that are more appropriate for the task. |
| Outcome: | The proposed methods are poorly suited for the problem and should be adapted to address the propagation of online harms. |
Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection (N18-2)
Copied to clipboard
| Challenge: | Existing methods that focus on a single tweet as input are likely to yield high false positive and negative rates. |
| Approach: | They propose a model that leverages intra-user and inter-user representation learning to improve hate speech detection on Twitter by suppressing the noise in a single Tweet. |
| Outcome: | The proposed model significantly improves the f-score of a strong bidirectional LSTM model by 10.1%. |
Multi-domain Hate Speech Detection Using Dual Contrastive Learning and Paralinguistic Features (2024.lrec-main)
Copied to clipboard
| Challenge: | a recent study shows that hate speech is spread on social networks and can have social and cultural effects . 41% of americans who took the survey have experienced some type of online harassment . |
| Approach: | They propose a hate speech detection model using contrastive learning loss combined with traditional cross-entropy loss. |
| Outcome: | The proposed model outperforms comparable models on heated topics from two datasets . the model scored macro-F1 on two- and five-class tasks and averaged for four domains compared . |