English
Related papers

Related papers: Toxicity Detection with Generative Prompt-based In…

200 papers

The age of social media is rife with memes. Understanding and detecting harmful memes pose a significant challenge due to their implicit meaning that is not explicitly conveyed through the surface text and image. However, existing harmful…

Computation and Language · Computer Science 2023-12-12 Hongzhan Lin , Ziyang Luo , Jing Ma , Long Chen

Generative vision-language models like Stable Diffusion demonstrate remarkable capabilities in creative media synthesis, but they also pose substantial risks of producing unsafe, offensive, or culturally inappropriate content when prompted…

Artificial Intelligence · Computer Science 2025-11-18 Xin Zhao , Xiaojun Chen , Bingshan Liu , Zeyao Liu , Zhendong Zhao , Xiaoyan Gu

Natural language generation tools are powerful and effective for generating content. However, language models are known to display bias and fairness issues, making them impractical to deploy for many use cases. We here focus on how fairness…

Computation and Language · Computer Science 2024-05-03 Kevin Stowe , Benny Longwill , Alyssa Francis , Tatsuya Aoyama , Debanjan Ghosh , Swapna Somasundaran

Large Language Models (LLMs) are now widely used in various applications, making it crucial to align their ethical standards with human values. However, recent jail-breaking methods demonstrate that this alignment can be undermined using…

Cryptography and Security · Computer Science 2023-12-11 Zhuo Zhang , Guangyu Shen , Guanhong Tao , Siyuan Cheng , Xiangyu Zhang

Data poisoning attacks manipulate training data to introduce unexpected behaviors into machine learning models at training time. For text-to-image generative models with massive training datasets, current understanding of poisoning attacks…

Cryptography and Security · Computer Science 2024-04-30 Shawn Shan , Wenxin Ding , Josephine Passananti , Stanley Wu , Haitao Zheng , Ben Y. Zhao

The rapid expansion of social media leads to a marked increase in hate speech, which threatens personal lives and results in numerous hate crimes. Detecting hate speech presents several challenges: diverse dialects, frequent code-mixing,…

Computation and Language · Computer Science 2025-07-01 Ruhina Tabasshum Prome , Tarikul Islam Tamiti , Anomadarshi Barua

This study targets a critical aspect of multi-modal LLMs' (LLMs&VLMs) inference: explicit controllable text generation. Multi-modal LLMs empower multi-modality understanding with the capability of semantic generation yet bring less…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Yuechen Zhang , Shengju Qian , Bohao Peng , Shu Liu , Jiaya Jia

This work proposes a training-free approach for the detection of LLMs-generated codes, mitigating the risks associated with their indiscriminate usage. To the best of our knowledge, our research is the first to investigate zero-shot…

Computation and Language · Computer Science 2023-10-10 Xianjun Yang , Kexun Zhang , Haifeng Chen , Linda Petzold , William Yang Wang , Wei Cheng

In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attackers can carefully curate input strings that mislead LLMs…

Computation and Language · Computer Science 2024-02-20 Zhengmian Hu , Gang Wu , Saayan Mitra , Ruiyi Zhang , Tong Sun , Heng Huang , Viswanathan Swaminathan

The strength of modern generative models lies in their ability to be controlled through text-based prompts. Typical "hard" prompts are made from interpretable words and tokens, and must be hand-crafted by humans. There are also "soft"…

Machine Learning · Computer Science 2023-06-02 Yuxin Wen , Neel Jain , John Kirchenbauer , Micah Goldblum , Jonas Geiping , Tom Goldstein

Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and…

Machine Learning · Computer Science 2024-10-02 Xuefeng Du , Reshmi Ghosh , Robert Sim , Ahmed Salem , Vitor Carvalho , Emily Lawton , Yixuan Li , Jack W. Stokes

Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. However, language models that are pretrained on large unlabeled web text corpora have been shown…

Computation and Language · Computer Science 2022-07-28 Farshid Faal , Ketra Schmitt , Jia Yuan Yu

With the recent rise of toxicity in online conversations on social media platforms, using modern machine learning algorithms for toxic comment detection has become a central focus of many online applications. Researchers and companies have…

Artificial Intelligence · Computer Science 2020-03-30 Ameya Vaidya , Feng Mai , Yue Ning

Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the influence of…

Computation and Language · Computer Science 2022-10-19 Atijit Anuchitanukul , Julia Ive , Lucia Specia

Social media platforms provide an environment where people can freely engage in discussions. Unfortunately, they also enable several problems, such as online harassment. Recently, Google and Jigsaw started a project called Perspective,…

Machine Learning · Computer Science 2017-02-28 Hossein Hosseini , Sreeram Kannan , Baosen Zhang , Radha Poovendran

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not…

Computation and Language · Computer Science 2024-01-25 Hongzhan Lin , Ziyang Luo , Wei Gao , Jing Ma , Bo Wang , Ruichao Yang

Online platforms have become an increasingly prominent means of communication. Despite the obvious benefits to the expanded distribution of content, the last decade has resulted in disturbing toxic communication, such as cyberbullying and…

Social and Information Networks · Computer Science 2023-09-04 Amit Sheth , Valerie L. Shalin , Ugur Kursuncu

A common approach for testing fairness issues in text-based classifiers is through the use of counterfactuals: does the classifier output change if a sensitive attribute in the input is changed? Existing counterfactual generation methods…

Computation and Language · Computer Science 2022-06-29 Zee Fryer , Vera Axelrod , Ben Packer , Alex Beutel , Jilin Chen , Kellie Webster

Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs). Unfortunately, recent studies have discovered such an evaluation may be inaccurate, inconsistent and unreliable. Furthermore, the…

Computation and Language · Computer Science 2022-03-24 Boxi Cao , Hongyu Lin , Xianpei Han , Fangchao Liu , Le Sun

Generic `toxicity' classifiers continue to be used for evaluating the potential for harm in natural language generation, despite mounting evidence of their shortcomings. We consider the challenge of measuring misogyny in natural language…

Computation and Language · Computer Science 2023-12-07 Aaron J. Snoswell , Lucinda Nelson , Hao Xue , Flora D. Salim , Nicolas Suzor , Jean Burgess