Existing strategies for managing risks from advanced AI systems often focus
on affecting what AI systems are developed and how they diffuse. However, this
approach becomes less feasible as the number of developers of advanced AI
grows, and impedes beneficial use-cases as well as harmful ones. In response,
we urge a complementary approach: increasing societal adaptation to advanced
AI, that is, reducing the expected negative impacts from a given level of
diffusion of a given AI capability. We introduce a conceptual framework which
helps identify adaptive interventions that avoid, defend against and remedy
potentially harmful uses of AI systems, illustrated with examples in election
manipulation, cyberterrorism, and loss of control to AI decision-makers. We
discuss a three-step cycle that society can implement to adapt to AI.
Increasing society's ability to implement this cycle builds its resilience to
advanced AI. We conclude with concrete recommendations for governments,
industry, and third-parties.

存在的管理高级人工智能系统风险的策略通常关注于影响开发什么样的人工智能系统以及它们如何扩散。然而，随着高级人工智能开发者数量的增加，这种方法变得越来越不可行，并且阻碍了有益的和有害的用例。我们呼吁采用一种补充方法：提高社会对高级人工智能的适应能力，即减少特定级别的人工智能能力扩散所带来的预期负面影响。我们引入了一个概念框架，用于识别避免、防范和纠正潜在有害的人工智能系统使用的适应性干预措施，并结合选举操纵、网络恐怖主义和人工智能决策者失控的示例进行说明。我们讨论了社会可以实施的适应人工智能的三个步骤循环。增强社会实施这一循环的能力将提高社会对高级人工智能的韧性。最后，我们为政府、行业和第三方提出具体建议。

先进人工智能的社会适应

Societal Adaptation to Advanced AI

In order to oversee advanced AI systems, it is important to understand their
underlying decision-making process. When prompted, large language models (LLMs)
can provide natural language explanations or reasoning traces that sound
plausible and receive high ratings from human annotators. However, it is
unclear to what extent these explanations are faithful, i.e., truly capture the
factors responsible for the model's predictions. In this work, we introduce
Correlational Explanatory Faithfulness (CEF), a metric that can be used in
faithfulness tests based on input interventions. Previous metrics used in such
tests take into account only binary changes in the predictions. Our metric
accounts for the total shift in the model's predicted label distribution, more
accurately reflecting the explanations' faithfulness. We then introduce the
Correlational Counterfactual Test (CCT) by instantiating CEF on the
Counterfactual Test (CT) from Atanasova et al. (2023). We evaluate the
faithfulness of free-text explanations generated by few-shot-prompted LLMs from
the Llama2 family on three NLP tasks. We find that our metric measures aspects
of faithfulness which the CT misses.

评估了 Llama2 系列的少样本提示 LLMs 生成的自由文本解释在三个 NLP 任务上的忠实性，并发现我们的度量考虑了 CT 遗漏的忠实性方面。

概率也很重要：大型语言模型中自由文本解释的忠实度的更为准确的评估指标

The Probabilities Also Matter: A More Faithful Metric for Faithfulness  of Free-Text Explanations in Large Language Models

In this short consensus paper, we outline risks from upcoming, advanced AI
systems. We examine large-scale social harms and malicious uses, as well as an
irreversible loss of human control over autonomous AI systems. In light of
rapid and continuing AI progress, we propose priorities for AI R&D and
governance.

通过研究先进的人工智能系统，我们指出了即将到来的风险，包括大规模社会伤害和恶意使用，以及人类对自主人工智能系统失去控制的不可逆性。鉴于人工智能的迅速发展，我们提出了人工智能研发和治理的优先事项。