Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Chi, Zhu, Changjia, Xiong, Junjie, Xu, Xiaoran, Li, Lingyao, Liu, Yao, Lu, Zhuo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.05775
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918124215861248
author Zhang, Chi
Zhu, Changjia
Xiong, Junjie
Xu, Xiaoran
Li, Lingyao
Liu, Yao
Lu, Zhuo
author_facet Zhang, Chi
Zhu, Changjia
Xiong, Junjie
Xu, Xiaoran
Li, Lingyao
Liu, Yao
Lu, Zhuo
contents Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language generation and understanding. These models enable beneficial applications such as content generation, question and answering (Q&A), programming, and code reasoning. Meanwhile, they also pose serious risks by inadvertently or intentionally producing toxic, offensive, or biased content. This dual role of LLMs, both as powerful tools for solving real-world problems and as potential sources of harmful language, presents a pressing sociotechnical challenge. In this survey, we systematically review recent studies spanning unintentional toxicity, adversarial jailbreaking attacks, and content moderation techniques. We propose a unified taxonomy of LLM-related harms and defenses, analyze emerging multimodal and LLM-assisted jailbreak strategies, and assess mitigation efforts, including reinforcement learning with human feedback (RLHF), prompt engineering, and safety alignment. Our synthesis highlights the evolving landscape of LLM safety, identifies limitations in current evaluation methodologies, and outlines future research directions to guide the development of robust and ethically aligned language technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05775
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
Zhang, Chi
Zhu, Changjia
Xiong, Junjie
Xu, Xiaoran
Li, Lingyao
Liu, Yao
Lu, Zhuo
Computation and Language
Computers and Society
Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language generation and understanding. These models enable beneficial applications such as content generation, question and answering (Q&A), programming, and code reasoning. Meanwhile, they also pose serious risks by inadvertently or intentionally producing toxic, offensive, or biased content. This dual role of LLMs, both as powerful tools for solving real-world problems and as potential sources of harmful language, presents a pressing sociotechnical challenge. In this survey, we systematically review recent studies spanning unintentional toxicity, adversarial jailbreaking attacks, and content moderation techniques. We propose a unified taxonomy of LLM-related harms and defenses, analyze emerging multimodal and LLM-assisted jailbreak strategies, and assess mitigation efforts, including reinforcement learning with human feedback (RLHF), prompt engineering, and safety alignment. Our synthesis highlights the evolving landscape of LLM safety, identifies limitations in current evaluation methodologies, and outlines future research directions to guide the development of robust and ethically aligned language technologies.
title Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
topic Computation and Language
Computers and Society
url https://arxiv.org/abs/2508.05775