GenIC uses a Mistral-based classifier and a T5-based generator to complete knowledge graph facts from a head entity, outperforming simple baselines on FB15k-237, WN18RR, and CoDEx, with evaluation caveats.
Advances in neural information processing systems, 26, 2013
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GenIC: An LLM-Based Framework for Instance Completion in Knowledge Graphs
GenIC uses a Mistral-based classifier and a T5-based generator to complete knowledge graph facts from a head entity, outperforming simple baselines on FB15k-237, WN18RR, and CoDEx, with evaluation caveats.