aiqbench analysis
This survey provides a critical taxonomy of Large Language Model harms and defenses, moving beyond simple safety checks to address adversarial jailbreaks and unintentional toxicity. By evaluating mitigation strategies like RLHF and prompt engineering against emerging multimodal threats, the paper outlines essential research directions for building robust, ethically aligned language technologies. It serves as a foundational resource for researchers navigating the complex trade-offs between model capability and content moderation in sociotechnical systems.
Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM
arXiv:2508.05775v3 Announce Type: replace Abstract: Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language generation and understanding. Meanwhile, they pose risks by inadvertently producing toxic, offensive, or biased content. This dual role of LLMs, both as powerful tools for text generation and as potential sources of harmful language, presents a pressing sociotechnical challenge. In this survey, we systematically review recent studies encompassing unintentional toxicity, adversarial jailbreak attacks, and comprehensive mitigation strategies. We explore LLMs' dual role as both generators of harm and enablers of safety through detection, classification, content moderation, and prevention. 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 review highlights the evolving landscape of LLM safety and identifies limitations in current evaluation methodologies. Ultimately, our review outlines future research directions to guide the development of robust and ethically aligned language technologies.
Abstract:Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language generation and understanding. Meanwhile, they pose risks by inadvertently producing toxic, offensive, or biased content. This dual role of LLMs, both as powerful tools for text generation and as potential sources of harmful language, presents a pressing sociotechnical challenge. In this survey, we systematically review recent studies encompassing unintentional toxicity, adversarial jailbreak attacks, and comprehensive mitigation strategies. We explore LLMs' dual role as both generators of harm and enablers of safety through detection, classification, content moderation, and prevention. 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 review highlights the evolving landscape of LLM safety and identifies limitations in current evaluation methodologies. Ultimately, our review outlines future research directions to guide the development of robust and ethically aligned language technologies.
Computation and Language (cs.CL); Computers and Society (cs.CY)
arXiv:2508.05775 [cs.CL]
(or arXiv:2508.05775v3 [cs.CL] for this version)
Full text under the publisher's open licence · 178 words
Related coverage
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · Sep 18, 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026
Research Note: Filtering Subversion-Relevant Information From Pretraining Data Is Feasible
LessWrong · Oct 5, 2026
Unpacking AI safety for enterprises
Cohere · Jun 4, 2026