English
Related papers

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

200 papers

Evidence-enhanced detectors present remarkable abilities in identifying malicious social text. However, the rise of large language models (LLMs) brings potential risks of evidence pollution to confuse detectors. This paper explores…

Computation and Language · Computer Science 2025-05-30 Herun Wan , Minnan Luo , Zhixiong Su , Guang Dai , Xiang Zhao

In this paper, we study the problem of detecting machine-generated text when the large language model (LLM) it is possibly derived from is unknown. We do so by apply ensembling methods to the outputs from DetectGPT classifiers (Mitchell et…

Computation and Language · Computer Science 2024-06-19 Ivan Ong , Boon King Quek

Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most…

Computation and Language · Computer Science 2021-06-15 Yung-Sung Chuang , Mingye Gao , Hongyin Luo , James Glass , Hung-yi Lee , Yun-Nung Chen , Shang-Wen Li

Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet most detectors still treat toxicity as an intrinsic property of isolated text. This position paper…

Machine Learning · Computer Science 2026-05-13 Sergei Berezin , Reza Farahbakhsh , Noel Crespi

Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…

Cryptography and Security · Computer Science 2025-10-21 Zongze Li , Jiawei Guo , Haipeng Cai

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…

Computation and Language · Computer Science 2026-05-26 Shaz Furniturewala , Arkaitz Zubiaga

Augmenting large language models (LLMs) with user-specific knowledge is crucial for real-world applications, such as personal AI assistants. However, LLMs inherently lack mechanisms for prompt-driven knowledge capture. This paper…

Computation and Language · Computer Science 2024-02-02 Tolga Çöplü , Arto Bendiken , Andrii Skomorokhov , Eduard Bateiko , Stephen Cobb , Joshua J. Bouw

Retrained large language models (LLMs) have become extensively used across various sub-disciplines of natural language processing (NLP). In NLP, text classification problems have garnered considerable focus, but still faced with some…

Computation and Language · Computer Science 2023-12-05 Zhiqiang Wang , Yiran Pang , Yanbin Lin

Risk perception is subjective, and youth's understanding of toxic content differs from that of adults. Although previous research has conducted extensive studies on toxicity detection in social media, the investigation of youth's unique…

Computation and Language · Computer Science 2025-08-05 Yaqiong Li , Peng Zhang , Lin Wang , Hansu Gu , Siyuan Qiao , Ning Gu , Tun Lu

Filtering and annotating textual data are routine tasks in many areas, like social media or news analytics. Automating these tasks allows to scale the analyses wrt. speed and breadth of content covered and decreases the manual effort…

Computation and Language · Computer Science 2024-06-27 Simon Münker , Kai Kugler , Achim Rettinger

Employing language models to generate explanations for an incoming implicit hate post is an active area of research. The explanation is intended to make explicit the underlying stereotype and aid content moderators. The training often…

Computation and Language · Computer Science 2024-06-07 Neemesh Yadav , Sarah Masud , Vikram Goyal , Vikram Goyal , Md Shad Akhtar , Tanmoy Chakraborty

The proliferation of Internet memes in the age of social media necessitates effective identification of harmful ones. Due to the dynamic nature of memes, existing data-driven models may struggle in low-resource scenarios where only a few…

Computation and Language · Computer Science 2024-11-11 Jianzhao Huang , Hongzhan Lin , Ziyan Liu , Ziyang Luo , Guang Chen , Jing Ma

Warning: this paper includes model outputs showing offensive content. Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multimodal image/text generation. However, these models might also…

Computation and Language · Computer Science 2023-12-20 Xinpeng Wang , Xiaoyuan Yi , Han Jiang , Shanlin Zhou , Zhihua Wei , Xing Xie

Text moderation for user generated content, which helps to promote healthy interaction among users, has been widely studied and many machine learning models have been proposed. In this work, we explore an alternative perspective by…

Computation and Language · Computer Science 2021-09-21 Fei Tan , Yifan Hu , Kevin Yen , Changwei Hu

Using prompts to explore the knowledge contained within pre-trained language models for downstream tasks has now become an active topic. Current prompt tuning methods mostly convert the downstream tasks to masked language modeling problems…

Computation and Language · Computer Science 2022-10-25 Jiale Han , Shuai Zhao , Bo Cheng , Shengkun Ma , Wei Lu

The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access to the model or substantial training, which is impractical…

Computation and Language · Computer Science 2024-07-23 Rongwu Xu , Zi'an Zhou , Tianwei Zhang , Zehan Qi , Su Yao , Ke Xu , Wei Xu , Han Qiu

The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the-blanks problems (e.g., cloze tests) is a natural approach for…

Computation and Language · Computer Science 2020-11-10 Taylor Shin , Yasaman Razeghi , Robert L. Logan , Eric Wallace , Sameer Singh

Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment,…

Computation and Language · Computer Science 2024-04-26 Miaomiao Li , Jiaqi Zhu , Yang Wang , Yi Yang , Yilin Li , Hongan Wang

Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly…

Computation and Language · Computer Science 2024-08-13 Devansh Jain , Priyanshu Kumar , Samuel Gehman , Xuhui Zhou , Thomas Hartvigsen , Maarten Sap

As toxic language becomes nearly pervasive online, there has been increasing interest in leveraging the advancements in natural language processing (NLP), from very large transformer models to automatically detecting and removing toxic…

Computation and Language · Computer Science 2020-07-02 Austin P. Wright , Omar Shaikh , Haekyu Park , Will Epperson , Muhammed Ahmed , Stephane Pinel , Diyi Yang , Duen Horng Chau