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 recall and end-to-end answer quality. Our results demonstrate that attention-based models already possess a retrieval mechanism that can be elicited, rather than added as an external module.
@article{arxiv.2605.05806,
title = {Retrieval from Within: An Intrinsic Capability of Attention-Based Models},
author = {Elad Hoffer and Yochai Blau and Edan Kinderman and Ron Banner and Daniel Soudry and Boris Ginsburg},
journal= {arXiv preprint arXiv:2605.05806},
year = {2026}
}