Metraipolis › archive › dc_efaf3f43ef0e

Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing — arXiv:2608.11660

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11660
License (as archived)
CC0-1.0
Archived
2026-10-19T05:16:02.606Z
SHA-256 of the archived text
8b7e1092e00e1b5d740ac0f0d85d899a1ac5114060c562bd0e673685cd46a1f2
Stable URL of this page
https://metraipolis.com/documento/dc_efaf3f43ef0e

How to cite

Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing — arXiv:2608.11660 — arXiv (en), https://arxiv.org/abs/2608.11660 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efaf3f43ef0e (Metraipolis archive dc_efaf3f43ef0e, sha256 8b7e1092e00e1b5d740ac0f0d85d899a1ac5114060c562bd0e673685cd46a1f2)
BibTeX
@misc{dcefaf3f43ef0e,
  title = {Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing — arXiv:2608.11660},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11660},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efaf3f43ef0e; sha256 8b7e1092e00e1b5d740ac0f0d85d899a1ac5114060c562bd0e673685cd46a1f2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11660. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge quickly becomes outdated in a fast-changing world. This motivates knowledge editing (KE), which updates specific knowledge in an LLM without changing unrelated others. Recent works move from structured knowledge triples toward unstructured KE (UKE), where the edit is a free-form passage that may state multiple facts at once. Nonetheless, existing editors inject such a passage yet fail to use it: the edited model can recall the passage, but can neither answer atomic questions about its facts nor compose them into multi-hop reasoning. We attribute this missing property, which we term composability, to editors' passive reliance on the fixed passage as the sole learning source. In response, we cast editing as a proactive self-distillation from a privileged in-context state of the same model, which requires no external supervision. We further reveal that due to the novelty of the injected knowledge, the pre-edited model's own rollouts rarely cover it, which limits the effectiveness of pure on-policy distillation. To close this gap, we propose HPSE, which builds a hybrid rollout that steps in to place missing facts onto the student's own trajectory precisely where its coverage fails, while staying on-policy elsewhere. We theoretically analyze HPSE's advantage over pure on-policy distillation, and empirically establish its plug-and-play improvements across four LLM backbones and two KE editors under various scenarios.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 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/2608.11660 — 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 2026-10-19T05:08:46.711Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).