Signals 4 · free daily AI digest

The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora

Paper recorded by Signals 4 on 2026-09-21 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-21 on arXiv · recorded by Signals 4 on 2026-09-22

Category: cs.CL · 自然语言处理 · first seen 2026-09-22

Abstract

When a language model answers from a curated corpus via graph-based retrieval, a large grounding uplift does not establish reasoning over the retrieved structure: the context may already expose the gold answers. We propose exposure accounting, which classifies each gold item by whether the shown context exposes it and whether the answer recovers it. Its scalar reference is the copy ceiling, the re

Read on arXiv →

#6 most recent of 212 cs.CL papers we have recorded · ↑ newer: SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathol · ↓ older: Decomposing Error and Style in Automated Clinical Coding
Cite this page: The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora: the #6 most recent of 212 cs.CL papers we have recorded (as of 2026-09-21). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/the-copy-ceiling-an-input-exposure-control-for-ontology-grounded-generation-over.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions