Even the LLM Needs a Layer: a refusal battery for knowledge-graph competency evaluation

This record is a dated artifact record for a forthcoming paper, deposited before the paper exists and before the battery was run against the serving store. It argues from the published evidence that a language layer alone cannot certify its own answers. CodeSimpleQA measured the strongest frontier model at 62.9 percent on stable coding facts, with grounded retrieval near 71 percent against a parametric ceiling near 42 percent. GPTKB's 101-million-triple knowledge base built from a model showed only 31 percent of sampled triples verifiably true. KGQAGen's audit of 16 KGQA benchmarks found average factual correctness of 57 percent. The artifact is a 50-row human-authored refusal battery for knowledge-graph competency evaluation, frozen in advance: 40 knowledge rows, 8 refusal rows, 2 canary rows. The battery executes as a release gate against the live serving store, where an empty result over a complete schema is certified absence and a refusal is distinguishable from a failed retrieval. A paper describing the evaluation is under preparation. Files are restricted during the priority window as an independent-development record. Version 1, November 2026.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-22
DOI
https://doi.org/10.5281/zenodo.24430248
Primary Topic
Topic Modeling
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Even the LLM Needs a Layer: a refusal battery for knowledge-graph competency evaluation

Kazi Golam Rabbany
Zenodo (CERN European Organization for Nuclear Research)
Topic Modeling
preprint

Even the LLM Needs a Layer: a refusal battery for knowledge-graph competency evaluation

Kazi Golam Rabbany
preprint en

Abstract

This record is a dated artifact record for a forthcoming paper, deposited before the paper exists and before the battery was run against the serving store. It argues from the published evidence that a language layer alone cannot certify its own answers. CodeSimpleQA measured the strongest frontier model at 62.9 percent on stable coding facts, with grounded retrieval near 71 percent against a parametric ceiling near 42 percent. GPTKB's 101-million-triple knowledge base built from a model showed only 31 percent of sampled triples verifiably true. KGQAGen's audit of 16 KGQA benchmarks found average factual correctness of 57 percent. The artifact is a 50-row human-authored refusal battery for knowledge-graph competency evaluation, frozen in advance: 40 knowledge rows, 8 refusal rows, 2 canary rows. The battery executes as a release gate against the live serving store, where an empty result over a complete schema is certified absence and a refusal is distinguishable from a failed retrieval. A paper describing the evaluation is under preparation. Files are restricted during the priority window as an independent-development record. Version 1, November 2026.

Zenodo (CERN European Organization for Nuclear Research)
Narxoz University (KZ)
Topic Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon