# Tox-BART: Leveraging Toxicity Attributes for Explanation Generation of Implicit Hate Speech

arXiv: https://arxiv.org/abs/2406.03953 · HTML: https://mlsanity.com/paper/2406.03953/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Builds on (most cited first, 30 of 36)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering](https://mlsanity.com/paper/2005.00646/) (2020)
- [A Survey of Knowledge-Enhanced Text Generation](https://mlsanity.com/paper/2010.04389/) (2020)
- [A Knowledge-Enhanced Pretraining Model for Commonsense Story Generation](https://mlsanity.com/paper/2001.05139/) (2020)
- [On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations](https://mlsanity.com/paper/2203.13928/) (2022)
- [Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations](https://mlsanity.com/paper/2212.09865/) (2022)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [A Decade of Knowledge Graphs in Natural Language Processing: A Survey](https://mlsanity.com/paper/2210.00105/) (2022)
- [A Unified Deep Learning Architecture for Abuse Detection](https://mlsanity.com/paper/1802.00385/) (2018)
- [Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models](https://mlsanity.com/paper/2203.03131/) (2022)
- [COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements](https://mlsanity.com/paper/2306.01985/) (2023)
- [When did you become so smart, oh wise one?! Sarcasm Explanation in Multi-modal Multi-party Dialogues](https://mlsanity.com/paper/2203.06419/) (2022)
- [Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech](https://mlsanity.com/paper/2209.04889/) (2022)
- [Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks](https://mlsanity.com/paper/2105.05457/) (2021)
- [Beyond Denouncing Hate: Strategies for Countering Implied Biases and Stereotypes in Language](https://mlsanity.com/paper/2311.00161/) (2023)
- [Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection](https://mlsanity.com/paper/2205.03302/) (2022)

## Built on by (most cited first, 11 of 11)

- ["Cold, Calculated, and Condescending": How AI Identifies and Explains Ableism Compared to Disabled People](https://mlsanity.com/paper/2410.03448/) (2024)
- [On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMs](https://mlsanity.com/paper/2410.12600/) (2024)
- [SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes](https://mlsanity.com/paper/2412.20541/) (2024)
- [Graph-Guided Textual Explanation Generation Framework](https://mlsanity.com/paper/2412.12318/) (2024)
- [Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing](https://mlsanity.com/paper/2503.05280/) (2025)
- [Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning](https://mlsanity.com/paper/2505.11958/) (2025)
- [Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites](https://mlsanity.com/paper/2505.15297/) (2025)
- [Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classification](https://mlsanity.com/paper/2506.04693/) (2025)
- [Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure](https://mlsanity.com/paper/2604.25580/) (2026)
- [Reliable Evaluation Protocol for Low-Precision Retrieval](https://mlsanity.com/paper/2508.03306/) (2025)
- [Listening Between the Lines: Decoding Podcast Narratives with Language Modeling](https://mlsanity.com/paper/2511.05310/) (2025)

## Abstract (arXiv)

Employing language models to generate explanations for an incoming implicit hate post is an active area of research. The explanation is intended to make explicit the underlying stereotype and aid content moderators. The training often combines top-k relevant knowledge graph (KG) tuples to provide world knowledge and improve performance on standard metrics. Interestingly, our study presents conflicting evidence for the role of the quality of KG tuples in generating implicit explanations. Consequently, simpler models incorporating external toxicity signals outperform KG-infused models. Compared to the KG-based setup, we observe a comparable performance for SBIC (LatentHatred) datasets with a performance variation of +0.44 (+0.49), +1.83 (-1.56), and -4.59 (+0.77) in BLEU, ROUGE-L, and BERTScore. Further human evaluation and error analysis reveal that our proposed setup produces more precise explanations than zero-shot GPT-3.5, highlighting the intricate nature of the task.