一次近似ステアリング：重み適応を活性化ステアリングに変換する手法
First-Order Steering: Translating Weight Adaptation into Activation Steering
重み更新を活性化空間のステアリングベクトルとして一次近似する枠組みを提案し、複数行動の同時制御を可能にするモデルマージ手法HeRD-Mergingを開発した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Sri Pranav Kunda, Alexander Kurz, Tomas Dominik, Uri Maoz
分類: cs.LG, cs.AI, cs.CL
原文アブストラクト
Activation steering exploits interpretable directions in the residual stream to enable inference-time manipulation of model behavior. Composing steering vectors to apply multiple target behaviors simultaneously is important in various fields-including AI alignment and safety-but remains a challenge for existing activation steering methods. In contrast, prior work in model merging shows that target behaviors represented by learned weight adaptations can be combined with high accuracy. A method that translates weight adaptations into activation steering vectors could therefore extend prior work in model merging to generate composable steering vectors that better enable simultaneous inference-time behavioral control. For this, we introduce First-Order Steering, a formulation of activation steering as a first-order approximation of weight update matrices parameterized by a vector of steering strengths, and establish theoretical bounds on the approximation error of first-order steering. We then develop a novel model merging procedure, HeRD-Merging, which minimizes the first-order approximation error terms to enable higher first-order steering accuracy. Together, our method produces steering vectors that control both individual and composed behaviors more accurately than existing activation steering methods. Furthermore, HeRD-Merging matches the performance of conventional model-merging baselines, while producing weight adaptations that admit more accurate first-order steering vectors.