English
Related papers

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

200 papers

This paper describes our participation in the DEtection of TOXicity in comments In Spanish (DETOXIS) shared task 2021 at the 3rd Workshop on Iberian Languages Evaluation Forum. The shared task is divided into two related classification…

Computation and Language · Computer Science 2021-11-09 Angel Felipe Magnossão de Paula , Ipek Baris Schlicht

Despite the impressive performance of Large Language Models (LLMs) in software development activities, recent studies show the concern of introducing vulnerabilities into software codebase by AI programming assistants (e.g., Copilot,…

Software Engineering · Computer Science 2024-05-08 Sung Yong Kim , Zhiyu Fan , Yannic Noller , Abhik Roychoudhury

Large Language Models (LLMs) can now solve entire exams directly from uploaded PDF assessments, raising urgent concerns about academic integrity and the reliability of grades and credentials. Existing watermarking techniques either operate…

Computation and Language · Computer Science 2026-01-19 Ashish Raj Shekhar , Shiven Agarwal , Priyanuj Bordoloi , Yash Shah , Tejas Anvekar , Vivek Gupta

Perception of toxicity evolves over time and often differs between geographies and cultural backgrounds. Similarly, black-box commercially available APIs for detecting toxicity, such as the Perspective API, are not static, but frequently…

Computation and Language · Computer Science 2023-04-26 Luiza Pozzobon , Beyza Ermis , Patrick Lewis , Sara Hooker

The parallel evolution of Large Language Models (LLMs) with advanced code-understanding capabilities and the increasing sophistication of malware presents a new frontier for cybersecurity research. This paper evaluates the efficacy of…

Cryptography and Security · Computer Science 2026-01-15 Aniesh Chawla , Udbhav Prasad

Code review is a critical practice in modern software engineering, helping developers detect defects early, improve code quality, and facilitate knowledge sharing. With the rapid advancement of large language models (LLMs), a growing body…

Software Engineering · Computer Science 2026-02-17 Taufiqul Islam Khan , Shaowei Wang , Haoxiang Zhang , Tse-Hsun Chen

While Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, they often produce solutions that lack guarantees of correctness, robustness, and efficiency. This limitation is particularly acute in domains…

Software Engineering · Computer Science 2025-09-04 Yueke Zhang , Yifan Zhang , Kevin Leach , Yu Huang

Knowledge-Editing-based (KE-based) detoxification has emerged as a promising approach for mitigating harmful behaviours in Large Language Models. Existing evaluations, however, largely rely on automatic toxicity classifiers, implicitly…

Computation and Language · Computer Science 2026-02-12 Ming Dong , Shiyi Tang , Ziyan Peng , Guanyi Chen , Tingting He

Context: Contemporary code review tools are a popular choice for software quality assurance. Using these tools, reviewers are able to post a linkage between two patches during a review discussion. Large development teams that use a…

Software Engineering · Computer Science 2021-06-07 Dong Wang , Raula Gaikovina Kula , Takashi Ishio , Kenichi Matsumoto

Toxicity detection of text has been a popular NLP task in the recent years. In SemEval-2021 Task-5 Toxic Spans Detection, the focus is on detecting toxic spans within passages. Most state-of-the-art span detection approaches employ various…

Computation and Language · Computer Science 2021-08-16 Gunjan Chhablani , Abheesht Sharma , Harshit Pandey , Yash Bhartia , Shan Suthaharan

The proliferation of harmful online content--e.g., toxicity, spam, and negative sentiment--demands robust and adaptable moderation systems. However, prevailing moderation systems are centralized and task-specific, offering limited…

Computation and Language · Computer Science 2025-11-11 Rufan Zhang , Lin Zhang , Xianghang Mi

In modern software development workflows, the open-source software supply chain contributes significantly to efficient and convenient engineering practices. With increasing system complexity, using open-source software as third-party…

Software Engineering · Computer Science 2025-11-18 Zihe Yan , Kai Luo , Haoyu Yang , Yang Yu , Zhuosheng Zhang , Guancheng Li

Existing approaches to multilingual text detoxification are hampered by the scarcity of parallel multilingual datasets. In this work, we introduce a pipeline for the generation of multilingual parallel detoxification data. We also introduce…

Computation and Language · Computer Science 2025-08-18 Daniil Moskovskiy , Nikita Sushko , Sergey Pletenev , Elena Tutubalina , Alexander Panchenko

Modern software supply chains face an increasing threat from malicious code hidden in trusted components such as browser extensions, IDE extensions, and open-source packages. This paper introduces JavaSith, a novel client-side framework for…

Cryptography and Security · Computer Science 2025-05-28 Avihay Cohen

Data contamination presents a critical barrier preventing widespread industrial adoption of advanced software engineering techniques that leverage code language models (CLMs). This phenomenon occurs when evaluation data inadvertently…

Software Engineering · Computer Science 2024-11-19 Jialun Cao , Songqiang Chen , Wuqi Zhang , Hau Ching Lo , Shing-Chi Cheung

Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a method of generating…

Computation and Language · Computer Science 2019-12-17 Keita Kurita , Anna Belova , Antonios Anastasopoulos

The rapid growth in user generated content on social media has resulted in a significant rise in demand for automated content moderation. Various methods and frameworks have been proposed for the tasks of hate speech detection and toxic…

Computation and Language · Computer Science 2024-09-27 Elizaveta Korotkova , Isaac Chung

Content moderation typically combines the efforts of human moderators and machine learning models. However, these systems often rely on data where significant disagreement occurs during moderation, reflecting the subjective nature of…

Computation and Language · Computer Science 2025-09-01 Guillermo Villate-Castillo , Javier Del Ser , Borja Sanz

In different NLP tasks, detecting harmful content is crucial for online environments, especially with the growing influence of social media. However, previous research has two main issues: 1) a lack of data in low-resource settings, and 2)…

Computation and Language · Computer Science 2025-04-16 Zheng Hui , Zhaoxiao Guo , Hang Zhao , Juanyong Duan , Congrui Huang

The presence of toxic content has become a major problem for many online communities. Moderators try to limit this problem by implementing more and more refined comment filters, but toxic users are constantly finding new ways to circumvent…

Computation and Language · Computer Science 2018-12-06 Éloi Brassard-Gourdeau , Richard Khoury