English
Related papers

Related papers: ToxSearch: Evolving Prompts for Toxicity Search in…

200 papers

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Machine Learning · Computer Science 2025-08-21 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

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…

Software Engineering · Computer Science 2026-04-17 MD Awsaf Alam Anindya , Showvik Biswas , Anindya Iqbal , Jaydeb Sarker , Amiangshu Bosu

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Computation and Language · Computer Science 2025-02-14 Riccardo Cantini , Giada Cosenza , Alessio Orsino , Domenico Talia

Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial prompting. Existing automated methods are increasingly effective but each commits to a…

Computation and Language · Computer Science 2026-05-21 Abdullah Al Nomaan Nafi , Fnu Suya , Swarup Bhunia , Prabuddha Chakraborty

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

Computation and Language · Computer Science 2025-03-07 Honglin Mu , Han He , Yuxin Zhou , Yunlong Feng , Yang Xu , Libo Qin , Xiaoming Shi , Zeming Liu , Xudong Han , Qi Shi , Qingfu Zhu , Wanxiang Che

Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persistently develop…

Computation and Language · Computer Science 2026-03-17 Hankun Kang , Xin Miao , Jianhao Chen , Jintao Wen , Mayi Xu , Weiyu Zhang , Wenpeng Lu , Tieyun Qian

The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to…

Computation and Language · Computer Science 2023-10-20 Zhouxing Shi , Yihan Wang , Fan Yin , Xiangning Chen , Kai-Wei Chang , Cho-Jui Hsieh

Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge of "jailbreaking",…

Cryptography and Security · Computer Science 2024-09-02 Sibo Yi , Yule Liu , Zhen Sun , Tianshuo Cong , Xinlei He , Jiaxing Song , Ke Xu , Qi Li

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

Computation and Language · Computer Science 2025-03-26 Sravanti Addepalli , Yerram Varun , Arun Suggala , Karthikeyan Shanmugam , Prateek Jain

As large language models become integral to high-stakes applications, ensuring their robustness and fairness is critical. Despite their success, large language models remain vulnerable to adversarial attacks, where small perturbations, such…

Artificial Intelligence · Computer Science 2026-02-02 Danqing Chen , Tobias Ladner , Ahmed Rayen Mhadhbi , Matthias Althoff

We introduce TorchOpera, a compound AI system for enhancing the safety and quality of prompts and responses for Large Language Models. TorchOpera ensures that all user prompts are safe, contextually grounded, and effectively processed,…

Artificial Intelligence · Computer Science 2024-10-29 Shanshan Han , Zijian Hu , Alay Dilipbhai Shah , Han Jin , Yuhang Yao , Dimitris Stripelis , Zhaozhuo Xu , Chaoyang He

Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box…

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

Computation and Language · Computer Science 2024-06-25 Simone Tedeschi , Felix Friedrich , Patrick Schramowski , Kristian Kersting , Roberto Navigli , Huu Nguyen , Bo Li

Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process…

Human-Computer Interaction · Computer Science 2026-03-26 Minjae Lee , Minsuk Kahng

Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale. Detoxification is therefore important for safety and user trust, particularly when we want to reduce harmful…

Computation and Language · Computer Science 2026-02-04 Baturay Saglam , Dionysis Kalogerias

Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block…

Cryptography and Security · Computer Science 2026-01-13 Xi Ye , Yiwen Liu , Lina Wang , Run Wang , Geying Yang , Yufei Hou , Jiayi Yu

Optimization-based jailbreaks typically adopt the Toxic-Continuation setting in large vision-language models (LVLMs), following the standard next-token prediction objective. In this setting, an adversarial image is optimized to make the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Hee-Seon Kim , Minbeom Kim , Wonjun Lee , Kihyun Kim , Changick Kim

The proliferation of online toxic speech is a pertinent problem posing threats to demographic groups. While explicit toxic speech contains offensive lexical signals, implicit one consists of coded or indirect language. Therefore, it is…

Computation and Language · Computer Science 2024-05-21 Nhat M. Hoang , Xuan Long Do , Duc Anh Do , Duc Anh Vu , Luu Anh Tuan

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Machine Learning · Computer Science 2025-01-07 Ziwei Zheng , Junyao Zhao , Le Yang , Lijun He , Fan Li

High-quality prompts are crucial for Large Language Models (LLMs) to achieve exceptional performance. However, manually crafting effective prompts is labor-intensive and demands significant domain expertise, limiting its scalability.…

Computation and Language · Computer Science 2025-08-26 Zheng Dong , Luming Shang , Gabriela Olinto