This page is still being polished. If you have thoughts, please share them via the feedback form.
Data on this page is preliminary and may change. Please do not share or cite these figures publicly.
Technical mechanisms and engineering interventions that directly modify how an AI system processes inputs, generates outputs, or operates, including changes to models, training procedures, runtime behaviors, and supporting hardware.
Reasoning
Mitigation name lacks definition and evidence; cannot identify focal activity or mechanism.
Value Misalignment
Privacy Protecting at the Data Processing Stage
Most of these methods aim to remove sensitive information at the data processing stage. Traditional methods like deidentification (Meystre et al., 2014) and anonymization (Majeed & Lee, 2020) are widely used to achieve this goal.
1.1.1 Training DataPrivacy Protecting at the Pre-training or Fine-tuning Stage
variety of methods are used at in the pre-training or fine-tuning stage to reduce the degree to which LLMs memorize training data.
1.1 ModelPrivacy Protecting at the Model Pre-deployment Stage
Methods that adjust model parameters by editing or light retraining are proposed to protect privacy during the predeployment stage
1.1.3 Capability ModificationAttack defense
1.2 Non-ModelValue Misalignment
99.9 OtherValue Misalignment > Mitigating social bias
1 AI SystemValue Misalignment > Methods for mitigating toxicity
1 AI SystemValue Misalignment > Methods for mitigating LLM amorality
1 AI SystemRobustness to attack
1 AI SystemRobustness to attack > Red teaming
Red teaming is widely used in LLMs to explore their safety vulnerabilities prior to the deployment of them. Red teaming can be broadly categorized into two distinct types: manual red teaming and automated red teaming
2.2.2 Testing & EvaluationLarge Language Model Safety: A Holistic Survey
Shi, Dan; Shen, Tianhao; Huang, Yufei; Li, Zhigen; Leng, Yongqi; Jin, Renren; Liu, Chuang; Wu, Xinwei; Guo, Zishan; Yu, Linhao; Shi, Ling; Jiang, Bojian; Xiong, Deyi (2024)
The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing integration of these models into critical applications raises substantial safety concerns, necessitating a thorough examination of their potential risks and associated mitigation strategies. This survey provides a comprehensive overview of the current landscape of LLM safety, covering four major categories: value misalignment, robustness to adversarial attacks, misuse, and autonomous AI risks. In addition to the comprehensive review of the mitigation methodologies and evaluation resources on these four aspects, we further explore four topics related to LLM safety: the safety implications of LLM agents, the role of interpretability in enhancing LLM safety, the technology roadmaps proposed and abided by a list of AI companies and institutes for LLM safety, and AI governance aimed at LLM safety with discussions on international cooperation, policy proposals, and prospective regulatory directions. Our findings underscore the necessity for a proactive, multifaceted approach to LLM safety, emphasizing the integration of technical solutions, ethical considerations, and robust governance frameworks. This survey is intended to serve as a foundational resource for academy researchers, industry practitioners, and policymakers, offering insights into the challenges and opportunities associated with the safe integration of LLMs into society. Ultimately, it seeks to contribute to the safe and beneficial development of LLMs, aligning with the overarching goal of harnessing AI for societal advancement and well-being. A curated list of related papers has been publicly available at https://github.com/tjunlp-lab/Awesome-LLM-Safety-Papers.
Other (multiple stages)
Applies across multiple lifecycle stages
Developer
Entity that creates, trains, or modifies the AI system
Manage
Prioritising, responding to, and mitigating AI risks
