Metraipolis › archive › dc_8b52bd2c06b5
Encode Once, Answer Many: Internalizing Context via Parametric Flow — arXiv:2610.38356
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38356
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:08:53.625Z
- SHA-256 of the archived text
2f0a15836fc394a6c3c20d7c2aba4d526c18fd09b184962703d875eb539b923f- Stable URL of this page
https://metraipolis.com/documento/dc_8b52bd2c06b5
How to cite
Encode Once, Answer Many: Internalizing Context via Parametric Flow — arXiv:2610.38356 — arXiv (en), https://arxiv.org/abs/2610.38356 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8b52bd2c06b5 (Metraipolis archive dc_8b52bd2c06b5, sha256 2f0a15836fc394a6c3c20d7c2aba4d526c18fd09b184962703d875eb539b923f)
BibTeX
@misc{dc8b52bd2c06b5,
title = {Encode Once, Answer Many: Internalizing Context via Parametric Flow — arXiv:2610.38356},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38356},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8b52bd2c06b5; sha256 2f0a15836fc394a6c3c20d7c2aba4d526c18fd09b184962703d875eb539b923f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38356. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are typically adapted to a task either by placing knowledge in the input context, which keeps it external and re-encodes it on every call, or by fine-tuning, which internalizes it but demands a costly round of optimization per task. We aim to internalize the knowledge carried by a context directly into model parameters, without per-task optimization and without keeping the context in the input at inference time. To this end, we propose CLIK, a context-conditioned parameter generator that maps a given context to LoRA parameters for internalizing knowledge in a single forward pass through a Transformer encoder with cross-attention, requiring no test-time gradient updates. Once the generated LoRA is inserted into a frozen base model, the model answers downstream queries from the query alone, having internalized the context into its weights rather than re-reading it. Because the adapter depends only on the context, it is generated once and reused for every query on the same document, so the cost of reading that document is amortized across queries. On document question answering, CLIK substantially improves over the no-context base model and outperforms existing hypernetwork-based generators, while remaining behind a base model that reads the context directly, and it carries over to multi-turn dialogue without any multi-turn-specific training. Analysis further shows that the context-dependent part of the generated adapter concentrates in a compact and specific substructure. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.38356 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T06:07:08.472Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).