Metraipolis › archive › dc_73adb70bfa99

From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning — arXiv:2608.18581

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18581
License (as archived)
CC0-1.0
Archived
2026-10-18T13:45:13.190Z
SHA-256 of the archived text
cbb0232fa3b3f09a67399dbe00e8967fb57972778c92bd0d8191aff325f5d6ad
Stable URL of this page
https://metraipolis.com/documento/dc_73adb70bfa99

How to cite

From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning — arXiv:2608.18581 — arXiv (en), https://arxiv.org/abs/2608.18581 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73adb70bfa99 (Metraipolis archive dc_73adb70bfa99, sha256 cbb0232fa3b3f09a67399dbe00e8967fb57972778c92bd0d8191aff325f5d6ad)
BibTeX
@misc{dc73adb70bfa99,
  title = {From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning — arXiv:2608.18581},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18581},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73adb70bfa99; sha256 cbb0232fa3b3f09a67399dbe00e8967fb57972778c92bd0d8191aff325f5d6ad},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18581. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Although Large Language Models (LLMs) encode rich factual knowledge in their parameters, reliably recalling and verifying such knowledge remains a key bottleneck in factual question answering. Existing end-to-end methods entangle knowledge elicitation with reasoning, making it difficult to determine whether correct answers arise from parametric knowledge or the input context. To address this challenge, we propose VAKE (Verifiable Activation of Parametric KnowledgE), a two-stage reinforcement-learning framework that externalizes latent parametric knowledge through explicit Priming and transfers the acquired elicitation capability to implicit Reasoning. Given a query and an insufficient retrieved subgraph, the Priming policy explicitly inserts bridging triples as verifiable evidence, with supervision provided by rewards derived from answers generated by a separate frozen model over the augmented subgraph. Building on the policy learned during Priming, the Reasoning stage trains the model to answer from the original input, testing whether the capability acquired through explicit knowledge elicitation transfers to implicit reasoning. Experiments across seven benchmarks and models from 3B to 14B show that VAKE consistently outperforms standard baselines, including when transferring directly from HotpotQA to OOD datasets. LLM-based evaluation further shows that over 80% of the inserted triples provide factual bridging knowledge not derivable from the retrieved context, while more than half elicit knowledge inaccessible through direct prompting. These results suggest that VAKE activates latent parametric knowledge rather than copying the input context or memorizing dataset-specific associations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.18581 — 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 2026-10-18T13:41:17.958Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).