← 研踪 PaperTrailarXiv:2608.00023 · v3
Role Steering of Language Models for Social Simulations
首次提交 2026-07-10 06:07
版本更新 2026-11-17 12:15
雷达观测 2026-11-18 19:43
摘要
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. We also introduce CastVectors, which 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 contribution: 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. Our code is available at https://github.com/HCAI-Lab-GT/casting-call-vectors, and the role vectors and evaluation data at https://huggingface.co/datasets/HCAI-Lab-GT/casting-call-vectors.
作者备注:34 pages. Published at the Social Sim'26 Workshop, COLM 2026. Code: https://github.com/HCAI-Lab-GT/casting-call-vectors
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-17 12:15 · 最新观测版本
Role Steering of Language Models for Social Simulations
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. We also introduce CastVectors, which 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 contribution: 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. Our code is available at https://github.com/HCAI-Lab-GT/casting-call-vectors, and the role vectors and evaluation data at https://huggingface.co/datasets/HCAI-Lab-GT/casting-call-vectors.
查看此版本解读 →查看此版本原文 ↗