用概念器实现更精准的模型输出控制，优于传统向量叠加方法。
Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering
- 引入概念器作为激活向量的椭球区域表示，实现软投影控制。
- 在多个任务中，概念器方法优于传统单向量控制，组合任务性能提升。
- 支持布尔操作实现复合目标，适合需要精细调控的场景。
大语言模型已彻底改变人工智能，但可靠控制其输出仍具挑战。本文探索激活工程——通过推理时操纵预训练LLM的激活来控制输出。不同于传统使用单一引导向量的方法，我们引入概念器（conceptors），一种将激活向量集合表示为椭球区域的数学结构。概念器作为软投影矩阵，能更精确地控制复杂激活模式。实验表明，概念器在多个引导任务中表现优于传统方法。我们进一步对概念器进行布尔运算以实现复合引导目标，在一组任务上实证优于向量加法组合。这些结果凸显概念器作为有效引导大语言模型的潜力。代码已开源至github.com/jorispos/conceptorsteering。
原文摘要 · Abstract (English)
Large language models have transformed AI, yet reliably controlling their outputs remains a challenge. This paper explores activation engineering, where outputs of pre-trained LLMs are controlled by manipulating their activations at inference time. Unlike traditional methods using a single steering vector, we introduce conceptors - mathematical constructs that represent sets of activation vectors as ellipsoidal regions. Conceptors act as soft projection matrices and offer more precise control over complex activation patterns. Our experiments demonstrate that conceptors outperform traditional methods across multiple steering tasks. We further use Boolean operations on conceptors for combined steering goals that empirically outperform additively combining steering vectors on a set of tasks. These results highlight conceptors as a promising tool for more effective steering of LLMs. Our code is available on github.com/jorispos/conceptorsteering.
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。