Related papers: Real-Time Toxicity Filtering for Open-Source Code …

Memes, as a widely used mode of online communication, often serve as vehicles for spreading harmful content. However, limitations in data accessibility and the high costs of dataset curation hinder the development of robust meme moderation…

Toxicity detection algorithms, originally designed with reactive content moderation in mind, are increasingly being deployed into proactive end-user interventions to moderate content. Through a socio-technical lens and focusing on contexts…

Software supply chain attacks targeting the npm ecosystem have become increasingly sophisticated, leveraging obfuscation and complex logic to evade traditional detection mechanisms. Recently, large language models (LLMs) have attracted…

Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets face limitations: they rely on human annotators who…

Toxic language in Bengali remains prevalent, especially in online environments, with few effective precautions against it. Although text detoxification has seen progress in high-resource languages, Bengali remains underexplored due to…

The detrimental effects of toxicity in competitive online video games are widely acknowledged, prompting publishers to monitor player chat conversations. This is challenging due to the context-dependent nature of toxicity, often spread…

Eradication of code smells is often pointed out as a way to improve readability, extensibility and design in existing software. However, code smell detection in large systems remains time consuming and error-prone, partly due to the…

WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMARTER, we introduce SMARTER, a data-efficient two-stage framework for explainable content moderation…

Text detoxification is a textual style transfer (TST) task where a text is paraphrased from a toxic surface form, e.g. featuring rude words, to the neutral register. Recently, text detoxification methods found their applications in various…

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety…

As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…

Context: Code smells (CS) tend to compromise software quality and also demand more effort by developers to maintain and evolve the application throughout its life-cycle. They have long been catalogued with corresponding mitigating solutions…

Comments within source code are essential for developers to comprehend the code's purpose and ensure its correct usage. However, as codebases evolve, maintaining an accurate alignment between the comments and the code becomes increasingly…

On the world wide web, toxic content detectors are a crucial line of defense against potentially hateful and offensive messages. As such, building highly effective classifiers that enable a safer internet is an important research area.…

Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text…

Code reviews are a critical yet time-consuming aspect of modern software development, increasingly challenged by growing system complexity and the demand for faster delivery. This paper presents a study conducted at WirelessCar Sweden AB,…

In the dynamic landscape of open source software (OSS) development, understanding and addressing incivility within issue discussions is crucial for fostering healthy and productive collaborations. This paper presents a curated dataset of…

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 Transfer (TST) task, where…

We introduce a novel class of adversarial attacks on toxicity detection models that exploit language models' failure to interpret spatially structured text in the form of ASCII art. To evaluate the effectiveness of these attacks, we propose…

To date, toxicity mitigation in language models has almost entirely been focused on single-language settings. As language models embrace multilingual capabilities, it's crucial our safety measures keep pace. Recognizing this research gap,…