Injecting LLM-generated entities and IPC-style ontology labels into both retrieval and generation improves patent matching accuracy on PatentMatch by up to 17.68% over vanilla LLMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing the Patent Matching Capability of Large Language Models via the Memory Graph
Injecting LLM-generated entities and IPC-style ontology labels into both retrieval and generation improves patent matching accuracy on PatentMatch by up to 17.68% over vanilla LLMs.