# DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship

arXiv: https://arxiv.org/abs/2411.01844 · HTML: https://mlsanity.com/paper/2411.01844/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 67 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Builds on (most cited first, 24 of 24)

- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [COLD: A Benchmark for Chinese Offensive Language Detection](https://mlsanity.com/paper/2201.06025/) (2022)
- [Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation](https://mlsanity.com/paper/2204.11788/) (2022)
- [Offensive Language and Hate Speech Detection for Danish](https://mlsanity.com/paper/1908.04531/) (2019)
- [RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?](https://mlsanity.com/paper/2404.14397/) (2024)
- [Defining and Detecting Toxicity on Social Media: Context and Knowledge are Key](https://mlsanity.com/paper/2104.10788/) (2021)
- [A Framework of Severity for Harmful Content Online](https://mlsanity.com/paper/2108.04401/) (2021)
- [Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models](https://mlsanity.com/paper/2312.08303/) (2023)
- [Exploring ChatGPT for Toxicity Detection in GitHub](https://mlsanity.com/paper/2312.13105/) (2023)
- [Proactive Moderation of Online Discussions: Existing Practices and the Potential for Algorithmic Support](https://mlsanity.com/paper/2211.16525/) (2022)
- [Fine-Tuning Llama 2 Large Language Models for Detecting Online Sexual Predatory Chats and Abusive Texts](https://mlsanity.com/paper/2308.14683/) (2023)
- [Comparing the Perceived Legitimacy of Content Moderation Processes: Contractors, Algorithms, Expert Panels, and Digital Juries](https://mlsanity.com/paper/2202.06393/) (2022)
- [Designing Word Filter Tools for Creator-led Comment Moderation](https://mlsanity.com/paper/2202.08818/) (2022)
- [RECAST: Enabling User Recourse and Interpretability of Toxicity Detection Models with Interactive Visualization](https://mlsanity.com/paper/2102.04427/) (2021)
- [ModSandbox: Facilitating Online Community Moderation Through Error Prediction and Improvement of Automated Rules](https://mlsanity.com/paper/2210.09569/) (2022)
- [SexWEs: Domain-Aware Word Embeddings via Cross-lingual Semantic Specialisation for Chinese Sexism Detection in Social Media](https://mlsanity.com/paper/2211.08447/) (2022)
- ["There's so much responsibility on users right now:" Expert Advice for Staying Safer From Hate and Harassment](https://mlsanity.com/paper/2302.08057/) (2023)

## Built on by (most cited first, 7 of 7)

- [Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards](https://mlsanity.com/paper/2506.04975/) (2025)
- [Combating Toxic Language: A Review of LLM-Based Strategies for Software Engineering](https://mlsanity.com/paper/2504.15439/) (2025)
- ["Harmless to You, Hurtful to Me!": Investigating the Detection of Toxic Languages Grounded in the Perspective of Youth](https://mlsanity.com/paper/2508.02094/) (2025)
- [Do You Feel Comfortable? Detecting Hidden Conversational Escalation in AI Chatbots](https://mlsanity.com/paper/2512.06193/) (2025)
- [SoulSeek: Exploring the Use of Social Cues in LLM-based Information Seeking](https://mlsanity.com/paper/2601.01094/) (2026)
- [Power Echoes: Investigating Moderation Biases in Online Power-Asymmetric Conflicts](https://mlsanity.com/paper/2603.01457/) (2026)
- [CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs](https://mlsanity.com/paper/2604.10502/) (2026)

## Abstract (arXiv)

Although there have been automated approaches and tools supporting toxicity censorship for social posts, most of them focus on detection. Toxicity censorship is a complex process, wherein detection is just an initial task and a user can have further needs such as rationale understanding and content modification. For this problem, we conduct a needfinding study to investigate people's diverse needs in toxicity censorship and then build a ChatGPT-based censorship tool named DeMod accordingly. DeMod is equipped with the features of explainable Detection and personalized Modification, providing fine-grained detection results, detailed explanations, and personalized modification suggestions. We also implemented the tool and recruited 35 Weibo users for evaluation. The results suggest DeMod's multiple strengths like the richness of functionality, the accuracy of censorship, and ease of use. Based on the findings, we further propose several insights into the design of content censorship systems.