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 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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.05806 [cs.LG] |
| (or arXiv:2605.05806v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.05806 arXiv-issued DOI via DataCite (pending registration) |
From: Elad Hoffer [view email]
[v1]
Thu, 7 May 2026 07:42:28 UTC (1,727 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。