LORex combines a trained candidate ranker with batched LLM reasoning to insert new concepts into taxonomies, outperforming twelve baselines on most benchmarks while overstating the average gain.
Title resolution pending
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
-
Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansion
LORex combines a trained candidate ranker with batched LLM reasoning to insert new concepts into taxonomies, outperforming twelve baselines on most benchmarks while overstating the average gain.