用连续激活调控评估大模型的语用推理梯度差异。
Continuous Interpretive Steering for Scalar Diversity
- 通过控制激活强度实现语用推理的渐变调节。
- 梯度调控使模型对不同标量项的隐含意义反应更精准。
- 适合研究语言模型语用能力或开发可控生成系统的人
实用推理本质上是分级的。不同词汇项引发的语用丰富程度各不相同。标量蕴含正是这一特性的体现，其蕴含强度在不同标量项间存在差异。然而，当前对大语言模型（LLMs）语用推理的评估多依赖提示工程。本研究提出连续解释性调优（CIS），将激活层面的调控强度作为连续变量，以探测分级语用理解。为此构建了新数据集GraSD，编码标量多样性等级。在四个LLM上的实验表明，统一激活调控虽整体提升语用推理，但消解了项间差异；而梯度激活调控则产生与标量多样性等级一致的差异化解释变化。这说明分级敏感性存在于表征空间中，可通过可控干预系统恢复。CIS与GraSD共同提供了一套评估LLMs分级语用敏感性的原则性框架。
原文摘要 · Abstract (English)
Pragmatic inference is inherently graded. Different lexical items give rise to pragmatic enrichment to different degrees. Scalar implicature exemplifies this property through scalar diversity, where implicature strength varies across scalar items. However, evaluations of pragmatic inference in large language models (LLMs) often rely on prompt-based manipulations. Beyond prompt-level effects, this study introduces Continuous Interpretive Steering (CIS), a method that probes graded pragmatic interpretation by treating activation-level steering strength as a continuous experimental variable. To support this analysis, this study introduces a new dataset, GraSD, which encodes graded scalar diversity. Experiments on four LLMs show that uniform activation steering increases pragmatic interpretations globally but collapses item-level variation, whereas graded activation steering yields differentiated interpretive shifts aligned with scalar diversity grades. It indicates that graded sensitivity is encoded in the representation space and can be systematically recovered through controlled intervention. Together, CIS and GraSD provide a principled framework for evaluating graded pragmatic sensitivity in LLMs.
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。