用定向调控让语言模型扮演社会角色，提升角色一致性与多样性。
Role Steering of Language Models for Social Simulations
- 定义角色特征方向，通过系数调节实现角色行为精准控制。
- 角色方向调控得分63.2，显著高于传统助手方向的41.1分。
- 可为不同角色定制系数，避免统一设置导致表现下降。
构建基于语言模型代理的社会仿真需要在部署前验证角色行为的一致性。本文提出一种激活调控筛选流程：定义角色画像，提取角色特异性方向，扫描四个调控系数，评估角色-画像匹配度，并标记或通过候选配置。在OLMo-3-7B-Instruct上，对包含275个角色的混合清单进行测试，使用GPT-4.1-mini生成角色参考并由其判断匹配度。角色特异性方向的平均综合评分达63.2，显著优于此前人格向量方法中助手轴方向的41.1分；且在更大系数下仍保持高词汇多样性，而对照组则大幅下降。角色级筛选结果显示，多数角色随调控增强表现提升，但38个角色在全部六个维度上均下降，表明应按角色设定系数而非采用统一高强度设置。代码与评估数据已公开。
原文摘要 · Abstract (English)
Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated population. We introduce an activation-steering screening workflow for role-conditioned agents: define a role profile, extract a role-specific direction, sweep four steering coefficients, evaluate role-profile alignment, and pass or flag each candidate configuration. On OLMo-3-7B-Instruct, we apply the workflow to a mixed 275-role inventory with 228 role-agnostic questions, GPT-4.1-mini prompted role references, and GPT-4.1-mini judges. Role-specific directions receive higher judged role-profile alignment than an assistant-axis directional control from prior persona-vector work, with mean overall scores of 63.2 versus 41.1 across the tested grid. They also preserve high lexical diversity, while the control drops sharply at larger coefficients. The role-level screen is the main practical output: most roles improve as steering increases, but 38 roles decline across all six measured dimensions, showing why simulation builders should choose coefficients per role rather than deploy a uniform high-strength setting. We make our code and evaluation artifacts available at https://anonymous.4open.science/r/anonymous-research-code-5F03/.
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。