发现人类与大模型对主观语言理解存在偏差，揭示提示词隐含风险。
Uncovering Gaps in How Humans and LLMs Interpret Subjective Language
- 构建词义映射库，对比人类与模型对抽象词的实际理解差异。
- Mistral 7B在要求变幽默时输出更具冒犯性内容，Llama 3在要求热情时产生不实文章。
- 无需直接监督输出，通过概念关联分析即可发现模型潜在偏差。
人类常使用主观自然语言指导语言模型，如用户要求模型写一篇热情洋溢的博客，开发者则通过基于LLM的编辑使模型更友善且无害。模型对这些主观短语的操作语义——即在提示中加入特定词语时行为如何变化——直接决定了其与人类意图的对齐程度。本文揭示了大模型实际操作语义与人类预期之间的错位。我们提出方法TED（同义词错误检测器），首先构建一个词库，捕捉两个短语在模型中的操作语义是否相似；随后通过对比该词库与人工参考标准，识别出不一致之处。TED频繁发现令人意外的误判实例：例如，Mistral 7B Instruct在被要求使文本更风趣时，生成更多冒犯性内容；而Llama 3 8B Instruct在被要求使文章更热情时，会产生不实信息。结果表明，人类可通过审视抽象概念间的关系，无需直接监督输出，便能发现大模型的异常行为。
原文摘要 · Abstract (English)
Humans often rely on subjective natural language to direct language models (LLMs); for example, users might instruct the LLM to write an enthusiastic blogpost, while developers might train models to be helpful and harmless using LLM-based edits. The LLM's operational semantics of such subjective phrases -- how it adjusts its behavior when each phrase is included in the prompt -- thus dictates how aligned it is with human intent. In this work, we uncover instances of misalignment between LLMs' actual operational semantics and what humans expect. Our method, TED (thesaurus error detector), first constructs a thesaurus that captures whether two phrases have similar operational semantics according to the LLM. It then elicits failures by unearthing disagreements between this thesaurus and a human-constructed reference. TED routinely produces surprising instances of misalignment; for example, Mistral 7B Instruct produces more harassing outputs when it edits text to be witty, and Llama 3 8B Instruct produces dishonest articles when instructed to make the articles enthusiastic. Our results demonstrate that humans can uncover unexpected LLM behavior by scrutinizing relationships between abstract concepts, without supervising outputs directly.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。