幽默或有说服力，但不是两者：评估LLM中细粒度多概念控制
Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs
AI总结：
研究评估了LLM中多概念控制的细粒度可控性，发现双概念设置下性能下降，揭示了模型在组合性上的局限性。
摘要：
大型语言模型（LLMs）具有强大的生成能力，但许多应用需要对特定文本概念进行显式且细粒度的控制，例如幽默、说服力或正式性。先前的提示和表示工程方法可以提供粗粒度或单一属性的控制，但系统评估多属性设置仍然有限。我们引入了一个评估框架，用于评估单个和双概念场景下的细粒度可控性，重点是语言上不同的概念对（例如说服力与幽默）。令人惊讶的是，在多个LLM和生成任务中，我们发现双概念设置下的性能往往下降，尽管所选概念原则上应是可分离的。这揭示了基于简单提示的控制的根本限制：即使概念在直觉上是独立的，模型也难以处理组合性。我们的框架提供了系统证据证明这一差距，并为未来方法测量多概念控制能力提供了系统的方法。
英文摘要：
Large Language Models (LLMs) offer strong generative capabilities, but many applications require explicit and \textit{fine-grained} control over specific textual concepts, such as humor, persuasiveness, or formality. Prior approaches in prompting and representation engineering can provide coarse or single-attribute control, but systematic evaluation of multi-attribute settings remains limited. We introduce an evaluation framework for fine-grained controllability for both single- and dual-concept scenarios, focusing on linguistically distinct concept pairs (e.g., persuasiveness vs.~humor). Surprisingly, across multiple LLMs and generative tasks, we find that performance often drops in the dual-concept setting, even though the chosen concepts should in principle be separable. This reveals a fundamental limitation of naive prompting-based control: models struggle with compositionality even when concepts are intuitively independent. Our framework provides systematic evidence of this gap and offers a principled approach for measuring the ability of future methods for multi-concept control.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
