测试36个大模型发现，主流语言模型引导方法效果不稳定，部分反而变差。
Steering off Course: Reliability Challenges in Steering Language Models
- 在14类共36个大小从1.5B到70B的模型上测试三种引导方法
- 多数模型引导无效，部分甚至导致性能下降
- 揭示现有方法底层假设存在根本缺陷，不适用于大规模场景
语言模型的引导方法作为微调的轻量替代方案，可实现对模型激活值的定向修改。然而，以往研究仅在少数模型上评估，缺乏对方法鲁棒性的全面理解。本文系统考察了三种主流引导方法——DoLa、函数向量和任务向量。与先前研究仅测试少量模型不同，我们测试了多达36个模型，涵盖14个模型家族，参数规模从1.5B到70B。实验表明，引导方法的有效性存在显著差异，大量模型未见提升，甚至出现性能退化。分析揭示这些方法的基础假设存在根本性缺陷，挑战其作为可扩展引导方案的可靠性。
原文摘要 · Abstract (English)
Steering methods for language models (LMs) have gained traction as lightweight alternatives to fine-tuning, enabling targeted modifications to model activations. However, prior studies primarily report results on a few models, leaving critical gaps in understanding the robustness of these methods. In this work, we systematically examine three prominent steering methods -- DoLa, function vectors, and task vectors. In contrast to the original studies, which evaluated a handful of models, we test up to 36 models belonging to 14 families with sizes ranging from 1.5B to 70B parameters. Our experiments reveal substantial variability in the effectiveness of the steering approaches, with a large number of models showing no improvement and at times degradation in steering performance. Our analysis demonstrate fundamental flaws in the assumptions underlying these methods, challenging their reliability as scalable steering solutions.
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。