שחזור מבפנים: יכולת אינטרינסית של מודלים מבוססי קשב

תקציר מקורי באנגליתarXiv:2605.05806v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decoder can instead retrieve directly from its own internal representations. We introduce INTRA (INTrinsic Retrieval via Attention), a framework where decoder attention queries score pre-encoded evidence chunks that are then directly reused as context for generation. By construction, INTRA unifies retrieval and generation, eliminating the retriever-generator mismatch typical of RAG pipelines. This design also amortizes context encoding by reusing precomputed encoder states across queries. On question-answering benchmarks, INTRA outperforms strong engineered retrieval pipelines on both evidence recal