Engaging in the deliberate generation of abnormal outputs from large language
models (LLMs) by attacking them is a novel human activity. This paper presents
a thorough exposition of how and why people perform such attacks. Using a
formal qualitative methodology, we interviewed dozens of practitioners from a
broad range of backgrounds, all contributors to this novel work of attempting
to cause LLMs to fail. We relate and connect this activity between its
practitioners' motivations and goals; the strategies and techniques they
deploy; and the crucial role the community plays. As a result, this paper
presents a grounded theory of how and why people attack large language models:
LLM red teaming in the wild.

大规模语言模型攻击的动机、策略和技术以及社区的重要角色。

召唤恶魔并束缚它：野外 LLM 红队行动的一个基于实证的理论

Summon a Demon and Bind it: A Grounded Theory of LLM Red Teaming in the  Wild

Today, using Large-scale generative Language Models (LLMs) it is possible to
simulate free responses to interview questions like those traditionally
analyzed using qualitative research methods. Qualitative methodology
encompasses a broad family of techniques involving manual analysis of
open-ended interviews or conversations conducted freely in natural language.
Here we consider whether artificial "silicon participants" generated by LLMs
may be productively studied using qualitative methods aiming to produce
insights that could generalize to real human populations. The key concept in
our analysis is algorithmic fidelity, a term introduced by Argyle et al. (2023)
capturing the degree to which LLM-generated outputs mirror human
sub-populations' beliefs and attitudes. By definition, high algorithmic
fidelity suggests latent beliefs elicited from LLMs may generalize to real
humans, whereas low algorithmic fidelity renders such research invalid. Here we
used an LLM to generate interviews with silicon participants matching specific
demographic characteristics one-for-one with a set of human participants. Using
framework-based qualitative analysis, we showed the key themes obtained from
both human and silicon participants were strikingly similar. However, when we
analyzed the structure and tone of the interviews we found even more striking
differences. We also found evidence of the hyper-accuracy distortion described
by Aher et al. (2023). We conclude that the LLM we tested (GPT-3.5) does not
have sufficient algorithmic fidelity to expect research on it to generalize to
human populations. However, the rapid pace of LLM research makes it plausible
this could change in the future. Thus we stress the need to establish epistemic
norms now around how to assess validity of LLM-based qualitative research,
especially concerning the need to ensure representation of heterogeneous lived
experiences.

使用大规模生成性语言模型（LLMs）可以模拟自由回答面试问题，这种方法可以代替传统的定性研究方法；研究中提出了算法忠实度的概念，通过框架化定性分析发现人工和模型生成的参与者得到的主题相似，但在访谈的结构和语气上存在显著差异；LLMs 目前的算法忠实度不足以推广到人类群体，但未来可能会有改变；因此，有必要建立关于如何评估基于 LLMs 的定性研究的认知规范，特别是关于确保包含多样化生活经历的代表性。