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.
Shared evaluation datasets, testing frameworks, and measurement tools for AI systems.
Also in Shared Infrastructure
First, most existing evaluation metrics are tailored to specific benchmarks or tasks, providing a fragmented and limited view on LLMs (either capability or safety). This specificity highlights the pressing need for a unified evaluation metric/framework capable of comprehensively assessing LLMs across a wide range of scenarios. Such a metric would ensure these models are well-equipped to meet the demands of various tasks and contexts. Such a framework must account for differences in architectures, training data, and intended use cases among LLMs, offering a balance between consistency in evaluation and flexibility to accommodate different model designs.
Second, the rapid evolution of LLMs has exposed significant gaps in current evaluation methodologies, precipitating what some researchers describe as an “evaluation crisis”. This triggers emerging interests in the development of science of evaluations underscoring the need for universal evaluation theories and methodologies that can address complex, real-world scenarios (Zhan et al., 2024; Zhan, 2024).
Reasoning
Testing and evaluation activity assessing LLM safety through improved evaluation methodologies.
Future directions
Value Misalignment
99.9 OtherValue Misalignment > Mitigating social bias
1 AI SystemValue Misalignment > Privacy protection
1 AI SystemValue Misalignment > Methods for mitigating toxicity
1 AI SystemValue Misalignment > Methods for mitigating LLM amorality
1 AI SystemRobustness to attack
1 AI SystemLarge 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 (outside lifecycle)
Outside the standard AI system lifecycle
Developer
Entity that creates, trains, or modifies the AI system
Measure
Quantifying, testing, and monitoring identified AI risks
Other
