对大语言模型的心理操控
Psychological Steering of Large Language Models
AI总结：
本文提出一种心理操控框架，通过在语义校准的单元中进行无界、流畅性约束的扫描，改进大语言模型的干预方法，在14个模型中表现出色，优于传统方法。
摘要：
大语言模型（LLMs）通过激活层面的干预模拟了一致的人类行为。该范式正朝着残差流注入方法发展，依赖注入强度扫描来近似最佳干预设置。然而，现有方法限制了搜索空间和未校准的激活空间单元，可能错过最佳干预条件。因此，我们引入了一种心理操控框架，通过心理 artifacts 推导和校准残差流注入，并使用 IPIP-NEO-120 测量 OCEAN 人格模型来比较六种注入方法。我们发现，均差（MD）注入在11个LLM中优于 Personality Prompting（P$^2$），在开放性生成中表现更佳，提升了3.6%至16.4%。此外，P$^2$和MD注入的混合方法在13个LLM中优于两者，提升幅度从5.6%到21.9%。最后，我们表明MD注入符合线性表示假设，并提供了可靠的近似线性控制旋钮。然而，它们也诱导了OCEAN特质协方差模式，偏离了大五模型，表明学习表示与人类心理学之间存在差距。
英文摘要：
Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is converging on additive residual-stream injections, which rely on injection-strength sweeps to approximate optimal intervention settings. However, existing methods restrict the search space and sweep in uncalibrated activation-space units, potentially missing optimal intervention conditions. Thus, we introduce a psychological steering framework that performs unbounded, fluency-constrained sweeps in semantically calibrated units. Our method derives and calibrates residual-stream injections using psychological artifacts, and we use the IPIP-NEO-120, which measures the OCEAN personality model, to compare six injection methods. We find that mean-difference (MD) injections outperform Personality Prompting (P$^2$), an established baseline for OCEAN steering, in open-ended generation in 11 of 14 LLMs, with gains of 3.6\% to 16.4\%, overturning prior reports favoring prompting and positioning representation engineering as a new frontier in open-ended psychological steering. Further, we find that a hybrid of P$^2$ and MD injections outperforms both methods in 13 of 14 LLMs, with gains over P$^2$ ranging from 5.6\% to 21.9\% and from 3.3\% to 26.7\% over MD injections. Finally, we show that MD injections align with the Linear Representation Hypothesis and provide reliable, approximately linear control knobs for psychological steering. Nevertheless, they also induce OCEAN trait covariance patterns that depart from the Big Two model, suggesting a gap between learned representations and human psychology.
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。
