用角色向量引导大模型，比提示词更有效提升专业表现
Designing Role Vectors to Improve LLM Inference Behaviour
- 通过模型激活构造29个角色向量，直接操控内部表示
- 在相关任务上提升性能，无关任务影响微弱
- 适合想精准控制模型行为的研究者与开发者
角色对大型语言模型（LLMs）的影响已被广泛研究，但其对性能的直接影响仍不明确。本文提出一种新方法：通过角色向量引导模型行为，作为人物设定提示的替代方案。基于模型激活构建了29个角色向量，并在多个领域基准测试中评估其影响。研究考察了两种干预方式：(i) 激活叠加，强化特定角色方向；(ii) 方向消融，移除这些方向。结果表明，角色向量确实能有效引导模型行为，在相关领域任务中提升表现，而对无关任务影响较小。这说明操纵内部表征比基于角色的提示更能显著影响输出结果。
原文摘要 · Abstract (English)
The influence of personas on Large Language Models (LLMs) has been widely studied, yet their direct impact on performance remains uncertain. This work explores a novel approach to guiding LLM behaviour through role vectors, an alternative to persona-based prompting. We construct 29 role vectors derived from model activations and evaluate their impact on benchmark performance across multiple domains. Our analysis investigates whether these vectors can effectively steer models toward domain-specific expertise. We measure two key interventions: (i) activation addition, which reinforces role-specific directions, and (ii) directional ablation, which removes them. Results on well-established benchmarks indicate that role vectors do, in fact, influence model behaviour, improving task performance in relevant domains while marginally affecting unrelated tasks. This, in turn, suggests that manipulating internal model representations has a greater impact on outcomes than persona-based prompting.
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。