A new 'protoknowledge' analysis links lexical, hierarchical, and topological knowledge graph recall in LLMs to Text-to-SPARQL performance, offering a black-box route to detect semantic contamination.
Do not output anything else
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs
A new 'protoknowledge' analysis links lexical, hierarchical, and topological knowledge graph recall in LLMs to Text-to-SPARQL performance, offering a black-box route to detect semantic contamination.