Explaining Toxic Text via Knowledge Enhanced Text Generation
Warning: This paper contains content that is offensive and may be upsetting.Biased or toxic speech can be harmful to various demographic groups. Therefore, it is not only important for models to detect these speech, but to also output explanations of why a given text is toxic. Previous literature has mostly focused on classifying and detecting toxic speech, and existing efforts on explaining stereotypes in toxic speech mainly use standard text generation approaches, resulting in generic and repetitive explanations. Building on these prior works, we introduce a novel knowledge-informed encoder-decoder framework to utilize multiple knowledge sources to generate implications of biased text.Experiments show that our knowledge informed models outperform prior state-of-the-art models significantly, and can generate detailed explanations of stereotypes in toxic speech compared to baselines, both quantitatively and qualitatively.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderText GenerationSimilar Papers 제목 키워드 기반
Explaining Toxic Text via Knowledge Enhanced Text Generation
Biased or toxic speech can be harmful to various demographic groups. Therefore, it is not only important for models to detect these speech, but to also output explanations of why a given text is toxic. Previous literatur…
DecoderText GenerationJust KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes
Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framewo…
Knowledge DistillationKnowledge GraphsToxicity Detection can be Sensitive to the Conversational Context
User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on existing datasets will also tend to disregard context, makin…
Data AugmentationKnowledge DistillationSimulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models
The widespread practice of fine-tuning open-source Vision-Language Models (VLMs) raises a critical security concern: jailbreak vulnerabilities in base models may persist in downstream variants, enabling transferable atta…
Text Detoxification as Style Transfer in English and Hindi
This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfe…
Multi-Task LearningSentenceStyle TransferText Style Transfer+1