Metraipolis › archive › dc_3ba3aff7c5ca

When Does Better Confidence Improve a Knowledge-Graph Audit? — arXiv:2611.05877

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05877
License (as archived)
CC0-1.0
Archived
2026-11-05T18:18:39.941Z
SHA-256 of the archived text
4f4b8b947e8d0e4c77c1723e51cfd5d2901679f4d5d8f094a5196a92ce2aa855
Stable URL of this page
https://metraipolis.com/documento/dc_3ba3aff7c5ca

How to cite

When Does Better Confidence Improve a Knowledge-Graph Audit? — arXiv:2611.05877 — arXiv (en), https://arxiv.org/abs/2611.05877 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ba3aff7c5ca (Metraipolis archive dc_3ba3aff7c5ca, sha256 4f4b8b947e8d0e4c77c1723e51cfd5d2901679f4d5d8f094a5196a92ce2aa855)
BibTeX
@misc{dc3ba3aff7c5ca,
  title = {When Does Better Confidence Improve a Knowledge-Graph Audit? — arXiv:2611.05877},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05877},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ba3aff7c5ca; sha256 4f4b8b947e8d0e4c77c1723e51cfd5d2901679f4d5d8f094a5196a92ce2aa855},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05877. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Confidence estimates guide human review in LLM-built knowledge graphs, but better error prediction can yield little improvement in an audit. We study this gap through repairability, selection headroom and label validity. Modelling non-adaptive auditing as budgeted covering, we characterise the minimal decision-relevant error statistics and bound the regret of scalar-preserving first-order planning by a structural mass $\Delta^{\mathrm{cl}}$. We simulate ideal repair against benchmark-aligned labels for five extraction configurations and two cross-document graphs on Re-DocRED, followed by frozen confirmation on test and replication on 500 hash-selected training documents. On the held-out cross-document graphs, an error-rate $\times$ fan-out queue leaves 3.98-4.74 percentage points more errors than a joint model with the same actions. By comparison, opening shared actions for that joint planner reduces residual errors by 0.89-1.43 points relative to its own fact-only plans, in point estimates. Equivalence between joint and independent-block models remains inconclusive. Generic LLM verification improves three of four model-budget configurations on each held-out set. LLM adjudication identifies possible benchmark omissions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.05877 — 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 2026-11-05T18:13:03.940Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).