用对比方法调节大模型的时间偏好，实现短期与长期决策的双向控制。
Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition
- 通过对比训练识别模型中时间跨度的线性方向
- 在金钱延迟选择任务中显著改变模型的延迟偏好阈值
- 适合关注决策偏差、长期规划安全性的研究者
我们研究了大语言模型Qwen3-32B中时间跨度的线性表示，并利用其改变模型的时间相关偏好、推荐和能力。通过在教师强制的时间选择答案上训练对比线性探测器，我们在模型残差流中找到了短期与长期的方向。在保留的二元时间选择任务、分布外货币时间选择任务以及TravelPlanner能力基准上评估了对比激活添加的调控效果。核心结果表明，时间跨度方向可通过简单对比线性探测器识别，并用于调控以引发显著的双向偏好变化。在奖励大小与延迟变化的分布外货币选择任务中，调控显著地使模型对较小立即奖励与较大延迟奖励的无差异阈值发生双向移动。进一步显示，在适度时间调控下，规划相关能力指标有所提升。这些结果表明，模型的时间偏好可测量且可调控，对涉及延迟成本与收益的AI建议系统及长周期规划的安全性问题具有重要意义。
原文摘要 · Abstract (English)
We study linear representations of temporal horizon in the large language model Qwen3-32B and use them to change the model's time-related preferences, recommendations, and capabilities. We train contrastive linear probes on teacher-forced temporal-choice answers to find a short-term versus long-term direction in the model's residual stream, and evaluate contrastive activation-addition steering on a held-out binary temporal-choice task, an out-of-distribution monetary intertemporal-choice task, and a TravelPlanner capability benchmark. The central result is that temporal-horizon directions can be identified with simple contrastive linear probes and then used for steering to induce large, bidirectional preference changes. On an out-of-distribution monetary choice task that varies reward size and delay, steering strongly shifts the model's indifference threshold between smaller-sooner and larger-later rewards in both directions. We further show improvements on a planning-related capability metric under moderate temporal steering. These results suggest that model intertemporal preferences are measurable and steerable, which is relevant for AI systems that give advice involving delayed costs and benefits, and for safety questions about long-horizon planning.
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。