Metraipolis › archive › dc_c708a91399bb
The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora — arXiv:2609.24885
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24885
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:50:15.276Z
- SHA-256 of the archived text
0d761ea7d7ae102cf1078c0bdfc3f54e7738422578b0f8bd002230b97700cff6- Stable URL of this page
https://metraipolis.com/documento/dc_c708a91399bb
How to cite
The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora — arXiv:2609.24885 — arXiv (en), https://arxiv.org/abs/2609.24885 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c708a91399bb (Metraipolis archive dc_c708a91399bb, sha256 0d761ea7d7ae102cf1078c0bdfc3f54e7738422578b0f8bd002230b97700cff6)
BibTeX
@misc{dcc708a91399bb,
title = {The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora — arXiv:2609.24885},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24885},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c708a91399bb; sha256 0d761ea7d7ae102cf1078c0bdfc3f54e7738422578b0f8bd002230b97700cff6},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24885. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We built a node that grounds a replaceable language model in a maintained ontology corpus, then asked what its successful-looking evaluation could support. Across ten models, grounding raised target-name recall from 0.265 unaided to about 0.92. A copy baseline, the recall a verbatim copy of the shown context already achieves, scores 0.964, and every model sits 0.022 to 0.067 below it. Copying therefore scores higher on this limited recall measure, which does not assess whether answers are better. The comparison tests what a recall score establishes; it does not test whether reasoning occurred, because a reasoned answer and a copy score alike when the answer name is already in context. We report exposure accounting (four counts classifying each gold item by whether the context exposed it and the answer recovered it) and a model-judged audit of 423 sampled item observations. A separate paired production study found a model-judged quality gain of +0.27 [+0.11, +0.45] on a 0-5 scale. Operational studies found failures that recall alone would not show: rephrasing questions out of the graph's vocabulary cut exposure from 0.964 to 0.328, yet the absence-keyed fallback would have fired on only 2 of 506; and inserting extracted facts degraded judged pages in every arm, so that step was disabled. Five-arm controls show that any well-formed on-corpus block beats no context but do not establish that the specific content matters, and no matched comparison against flat-text retrieval was run. The corpus is public and largely LLM-generated, which establishes neither training exposure nor novelty. Each study has its own outcome measure. Where gold derives from the injected corpus, we recommend reporting the accounting beside quality judgements, not in place of them. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2609.24885 — 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 2026-10-09T06:48:45.067Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).