ToxiShield: Promoting Inclusive Developer Communication through Real-Time Toxicity Filtering

• URL: http://arxiv.org/abs/2604.14408v1
• Date: Wed, 15 Apr 2026 20:46:40 GMT
• Title: ToxiShield: Promoting Inclusive Developer Communication through Real-Time Toxicity Filtering
• Abstract summary: ToxiShield is a browser extension for GitHub pull requests built using three modules.<n>Toxicity Filter -- to identify whether a text is toxic, Communication coach -- to facilitate just-in-time fine-grained toxicity categorization, and The Reframer -- that generates a revised, constructive alternative.<n>We trained and evaluated multiple deep learning and Large Language Models to identify the best choice for each module.
• Score: 1.9500886760872191
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Toxic interactions during code reviews can undermine teamwork and hinder productivity in software engineering (SE) teams. While prior studies explore toxicity detection and empirical investigation, they lack real-time detoxification tools to support the SE community. To address this gap, we present ToxiShield, a browser extension for GitHub pull requests that is built using three modules: i) Toxicity Filter -- to identify whether a text is toxic, ii) Communication coach -- to facilitate just-in-time fine-grained toxicity categorization with explanations, and iii) The Reframer -- that generates a revised, constructive alternative of a toxic text. For each module, we trained and evaluated multiple deep learning and Large Language Models (LLMs) to identify the best choice. A BERT-based binary detection model, trained on 38,761 code review samples, achieves 98% accuracy and an F1-score of 97% and is the selected one for the Toxicity Filter module. For the Communication Coach, prompt-tuned Claude 3.5 Sonnet achieved the best performance with 39% MCC and 42% F1 in multiclass toxicity classification with detailed reasoning. For Reframer, we evaluated five LLMs using a fine-tuning strategy on a dataset of 10,120 code review comments. The fine-tuned Llama 3.2 model achieves 95.27% style transfer accuracy, 97.03% fluency, 67.07% content preservation, and an 84% J-score. We further validated ToxiShield through a human evaluation using the Technology Acceptance Model with 10 participants, confirming its perceived usefulness and ease of adoption. ToxiShield sets a benchmark for advancing constructive communication in software engineering, driving inclusivity and healthier collaboration in open-source communities.

Related papers

• PSK@EEUCA 2026: Fine-Tuning Large Language Models with Synthetic Data Augmentation for Multi-Class Toxicity Detection in Gaming Chat [0.0]
  This paper describes our system for the EEUCA 2026 Shared Task on Understanding Toxic Behavior in Gaming Communities.<n>The task involves classifying World of Tanks chat messages into six toxicity categories: Non-toxic, Insults/Flaming, Other Offensive, Hate/Harassment, Threats, and Extremism.<n>We explore multiple approaches including encoder-based models, instruction-tuned LLMs with LoRA fine-tuning, hierarchical classification, one-vs-rest strategies, and various ensemble methods.
  arXiv  Detail & Related papers  (2026-05-08T03:48:31Z)
• Detoxification for LLM: From Dataset Itself [69.09071947137926]
  Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself.<n>We attempt to detoxify directly on raw corpora with SoCD (Soft Contrastive Decoding), which guides an LLM to localize and rewrite toxic spans in raw data while preserving semantics.<n>On GPT2-XL, HSPD attains state-of-the-art detoxification, reducing Toxicity Probability (TP) from 0.42 to 0.18 and Maximum Expected Toxicity (EMT) from 0.43 to 0.20.
  arXiv  Detail & Related papers  (2026-04-21T06:12:29Z)
• Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions [59.49967357689445]
  Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies.<n>This study presents a complete open-source dilated real-based framework for the development and validation of deep learning models for affective touch recognition in soft interactive companions.
  arXiv  Detail & Related papers  (2026-04-16T10:20:05Z)
• Real-Time Toxicity Filtering for Open-Source Code Reviews [1.9500886760872191]
  ToxiShield is a realtime browser extension that identifies and detoxifies toxic code reviews.<n>The framework comprises three modules: toxicity identification, reasoned multiclass classification, and code review detoxification.
  arXiv  Detail & Related papers  (2026-04-10T02:49:09Z)
• <think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs [60.169913160819]
  This paper explores the possibility of using synthetic toxic data as an alternative to human-generated data for training models for detoxification.<n>Experiments show that models fine-tuned on synthetic data consistently perform worse than those trained on human data.<n>The root cause is identified as a critical lexical diversity gap: LLMs generate toxic content using a small, repetitive vocabulary of insults that fails to capture the nuances and variety of human toxicity.
  arXiv  Detail & Related papers  (2025-09-10T07:48:24Z)
• Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing [49.85884082568318]
  ToxEdit is a toxicity-aware knowledge editing approach.<n>It dynamically detects toxic activation patterns during forward propagation.<n>It then routes computations through adaptive inter-layer pathways to mitigate toxicity effectively.
  arXiv  Detail & Related papers  (2025-05-28T12:37:06Z)
• Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models [81.62767292169225]
  We investigate knowledge forgetting in large language models with a focus on its generalisation.<n>We propose PerMU, a novel probability perturbation-based unlearning paradigm.<n>Experiments are conducted on a diverse range of datasets, including TOFU, Harry Potter, ZsRE, WMDP, and MUSE.
  arXiv  Detail & Related papers  (2025-02-27T11:03:33Z)
• Unveiling the Implicit Toxicity in Large Language Models [77.90933074675543]
  The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. We show that LLMs can generate diverse implicit toxic outputs that are exceptionally difficult to detect via simply zero-shot prompting. We propose a reinforcement learning (RL) based attacking method to further induce the implicit toxicity in LLMs.
  arXiv  Detail & Related papers  (2023-11-29T06:42:36Z)
• You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content [13.600755614321493]
  We investigate how we can use large language models (LLMs) to tackle the problem of toxic content online. We focus on three tasks; 1) Toxicity Classification, 2) Toxic Span Detection, and 3) Detoxification. We find that prompt learning achieves around 10% improvement in the toxicity classification task compared to the baselines.
  arXiv  Detail & Related papers  (2023-08-10T14:14:13Z)
• ToxiSpanSE: An Explainable Toxicity Detection in Code Review Comments [4.949881799107062]
  ToxiSpanSE is the first tool to detect toxic spans in the Software Engineering (SE) domain. Our model achieved the best score with 0.88 $F1$, 0.87 precision, and 0.93 recall for toxic class tokens.
  arXiv  Detail & Related papers  (2023-07-07T04:55:11Z)
• Interactive Code Generation via Test-Driven User-Intent Formalization [60.90035204567797]
  Large language models (LLMs) produce code from informal natural language (NL) intent. It is hard to define a notion of correctness since natural language can be ambiguous and lacks a formal semantics. We describe a language-agnostic abstract algorithm and a concrete implementation TiCoder.
  arXiv  Detail & Related papers  (2022-08-11T17:41:08Z)
• Automated Identification of Toxic Code Reviews: How Far Can We Go? [7.655225472610752]
  ToxiCR is a supervised learning-based toxicity identification tool for code review interactions. ToxiCR significantly outperforms existing toxicity detectors on our dataset.
  arXiv  Detail & Related papers  (2022-02-26T04:27:39Z)
• Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic [2.4815579733050153]
  This paper describes our approach to the Toxic Spans Detection problem. We propose BERToxic, a system that fine-tunes a pre-trained BERT model to locate toxic text spans in a given text. Our system significantly outperformed the provided baseline and achieved an F1-score of 0.683, placing Lone Pine in the 17th place out of 91 teams in the competition.
  arXiv  Detail & Related papers  (2021-04-08T04:46:14Z)
• RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models [93.151822563361]
  Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language, and the effectiveness of controllable text generation algorithms at preventing such toxic degeneration.
  arXiv  Detail & Related papers  (2020-09-24T03:17:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.