跳到正文
arXiv cs.AI· Junyi Fan·· 23 小时前AI 评分26

激活引导能否替代基于提示词的情感启动?基于 Llama-3.1-8B-Instruct 的数字孪生实验

Can Activation Steering Substitute for Prompt-Based Affective Priming in LLM Digital Twins?

AI 导读

研究用 Llama-3.1-8B-Instruct 在 100 个角色、感恩与失控两个领域上测试激活引导能否替代情感启动的写作任务。注入均值差方向可剂量依赖地移动操纵检验,在感恩领域某一强度(beta ~ 2.7)下与真实提示效果相当,但超过该强度后会过冲,且两个方向不对称。结构匹配的无注入基线显示,省略写作任务本身会抬高近端测量,替代效果因此取决于具体测量指标。

正文 · 原文

View PDF HTML (experimental)

Abstract:Affective priming -- asking participants to write about a recalled event, such as a time they felt grateful or lacked control, and then measuring the induced state and its spillover onto related judgments -- is a standard way to manipulate emotion in the social sciences, and it also shifts the responses of LLM-based digital twins. The writing task, however, requires generating a full text. We test whether activation steering can replace it. Using Llama-3.1-8B-Instruct on 100 personas in two domains (gratitude, lack of control), we compare a real-prompt path replicating the original Twin-2K-500 Mega Study (J2) with an injection path that skips the writing and adds a mean-difference direction, extracted from human writing, to the residual stream at varying strengths. The real-prompt effects fall between the original human and digital-twin effects in 5 of 6 comparisons. Injection shifts the manipulation check in a dose-dependent way and matches the real-prompt effect at one strength in the gratitude domain (beta ~ 2.7), but overshoots beyond it, on the proximal measure as well, and asymmetrically across the two directions. A structure-matched No-Injection baseline separates two sources of difference: omitting the writing task raises the proximal measure in both domains, whereas the injected direction itself moves a distal measure in the lack-of-control domain. Substitution is therefore measure-dependent: validity established for one way of inducing a state does not carry over uniformly to another.
Comments: Code, generation logs and analysis scripts: this https URL
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.22738 [cs.AI]
  (or arXiv:2611.22738v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.22738

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Junyi Fan [view email]
[v1] Tue, 17 Nov 2026 13:08:06 UTC (232 KB)

来源:arXiv cs.AI · arxiv.org