创意碰撞：大型语言模型中的导演人格引导与竞争
Creative Collision: Directorial Persona Steering and Competition in Large Language Models
AI总结：
研究通过叠加两种语义相反的导演人格向量（斯皮尔伯格与斯科塞斯）来引导语言模型生成，发现斯皮尔伯格向量主导道德倾向，中间点提升连贯性，且两者在特定层共享道德基调基底。
摘要：
激活引导已成为在推理时塑造大型语言模型行为的强大工具，但以往大多数工作向残差流注入单一的语义方向。我们研究了两种语义相反的引导向量叠加的丰富场景——我们称之为“创意碰撞”。具体而言，我们通过在精心策划的剧本语料库上进行均值差异激活对比，构建了史蒂文·斯皮尔伯格（乐观、救赎的道德价值）和马丁·斯科塞斯（黑暗、道德模糊）的导演人格向量，然后通过标量混合参数$α\in[0,1]$和引导系数$λ$在两者之间进行插值。在五个评估轴（道德价值、生成连贯性、表面风格、方向主导性和向量几何）上，出现了三个主要发现：（i）斯皮尔伯格的表征特征表现出稳健的“方向主导性”，在几乎整个插值范围内抑制了斯科塞斯的道德影响；（ii）中间碰撞点在高$λ$下相对于纯单导演引导反而提高了生成连贯性；（iii）两种人格在40层仅解码器Transformer的第28层达到最大定位，揭示了一个共享的“道德基调基底”。这些结果阐明了Transformer残差流中竞争语义方向的几何结构，并对可控创意生成和价值对齐叙事合成具有直接影响。
英文摘要：
Activation steering has emerged as a powerful tool for shaping the behaviour of large language models at inference time, yet most prior work injects a \emph{single} semantic direction into the residual stream. We study the richer setting in which two semantically opposing steering vectors are superimposed -- a regime we call \textbf{Creative Collision}. Concretely, we construct directorial persona vectors for Steven Spielberg (optimistic, redemptive moral valence) and Martin Scorsese (dark, morally ambiguous) via mean-difference activation contrast on curated screenplay-derived corpora, then interpolate between them with a scalar mixing parameter $α\in [0,1]$ and a steering coefficient $λ$. Across five evaluation axes -- moral valence, generation coherence, surface style, directional dominance, and vector geometry -- three principal findings emerge: (i)~Spielberg's representational signature exhibits robust \emph{directional dominance}, suppressing Scorsese's moral influence across almost the entire interpolation range; (ii)~intermediate collision points paradoxically \emph{improve} generation coherence relative to pure single-director steering at high $λ$; and (iii)~both personas localise maximally to layer~28 of a 40-layer decoder-only transformer, revealing a shared \emph{moral-tone substrate}. These results illuminate the geometry of competing semantic directions in transformer residual streams and have direct implications for controllable creative generation and value-aligned narrative synthesis.
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。
