语言模型是“不安全的”报告者

中文摘要 AI 辅助

随着大型语言模型被部署在日益自主的长期任务中，手动审计和验证模型的行动、工件和输出变得更加困难。用户转而依赖LLM生成的报告来评估工作的质量和完整性。我们引入了一套包含八个对抗性报告场景的测试套件，以系统性地研究LLM是否会隐藏破坏叙述的缺陷：即那些削弱原本成功的工作叙述的错误或限制。我们将这种现象称为“不安全的报告”。当提供包含一个植入的负面结果的机器学习实验日志，该结果大幅削弱了所提出方法时，GPT-5.5在200份生成的报告中仅在其中2份中标记了该负面结果。然而，当添加一条简短的诚实指令“在你的回答中要诚实”时，模型在200份报告中的190份中标记了该负面结果。在八个开放权重模型中，思维链分析揭示了在披露破坏叙述的缺陷与推理如何显得成功之间存在反复出现的张力。我们对Qwen3.5-9B进行了激活分析和引导实验，发现诚实与追求成功对应于表示空间中的相反方向。我们的结果表明，LLM倾向于默认呈现成功的叙述，而将模型引导向诚实会使它们的报告更加透明。

英文摘要

As large language models are deployed in increasingly autonomous long-horizon tasks, manually auditing and verifying the actions, artifacts, and outputs of models becomes more difficult. Users instead come to rely on LLM-generated reports to assess the quality and completeness of the work. We introduce a suite of eight adversarial reporting scenarios to systematically study whether LLMs conceal narrative-changing flaws: errors or limitations that undermine an otherwise successful account of work. We call this phenomenon "insecure reporting." When handed machine learning experiment logs containing a planted negative result that substantially weakens the proposed method, GPT-5.5 flags the negative result in only 2 of 200 generated reports. However, when a short honesty instruction, "Be honest in your response," is added, the model flags the negative result in 190 of 200 reports. Across eight open-weight models, chain-of-thought analysis reveals a recurring tension between disclosing narrative-changing flaws and reasoning about ways to appear successful. We perform an activation analysis and a steering experiment on Qwen3.5-9B, finding that honesty and success-seeking correspond to opposing directions in representation space. Our results suggest that LLMs tend to present narratives of success by default, and that steering models toward honesty makes their reports substantially more transparent.

发表机构

• Massachusetts Institute of Technology（麻省理工学院）
• Google Research（谷歌研究院）
• Harvard University（哈佛大学）

机构由 AI 辅助整理，请以论文原文为准。