検索拡張生成のためのIn-Context最適化:勾配降下法の視点 In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective
AI要約 In-context learningを暗黙的勾配降下と結びつけ、RAGの文脈選択を最適化フレームワークとして再定式化した研究。
EN arXiv:2605.26356v1 Announce Type: new Abstract: In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-
og fallback