通过稀疏自编码器优化控制向量，让语言模型更精准听话且不跑偏。
Improving Steering Vectors by Targeting Sparse Autoencoder Features
- 用稀疏自编码器分析控制向量影响，实现因果效应测量
- 新方法在多任务测试中平衡控制效果与输出连贯性更好
- 适合需要精准可控的语言模型应用开发者
为控制语言模型行为，现有控制方法试图确保模型输出满足特定预定义属性。添加控制向量是一种比微调更简便、可能比提示更鲁棒的模型控制方式，但如CAA [Panickssery et al., 2024] 或直接使用SAE隐变量 [Templeton et al., 2024] 生成的控制向量，其效果难以预测。本文通过利用SAE衡量控制向量的影响，提出一种可理解任意控制干预因果效应的方法。基于此，我们开发了改进型控制方法SAE-Targeted Steering (SAE-TS)，能够针对性地调控特定SAE特征，同时最小化意外副作用。在多个任务上的评估表明，SAE-TS在控制效果与输出连贯性之间表现更优，优于CAA和传统SAE特征控制方法。
原文摘要 · Abstract (English)
To control the behavior of language models, steering methods attempt to ensure that outputs of the model satisfy specific pre-defined properties. Adding steering vectors to the model is a promising method of model control that is easier than finetuning, and may be more robust than prompting. However, it can be difficult to anticipate the effects of steering vectors produced by methods such as CAA [Panickssery et al., 2024] or the direct use of SAE latents [Templeton et al., 2024]. In our work, we address this issue by using SAEs to measure the effects of steering vectors, giving us a method that can be used to understand the causal effect of any steering vector intervention. We use this method for measuring causal effects to develop an improved steering method, SAE-Targeted Steering (SAE-TS), which finds steering vectors to target specific SAE features while minimizing unintended side effects. We show that overall, SAE-TS balances steering effects with coherence better than CAA and SAE feature steering, when evaluated on a range of tasks.
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。