A multi-stage Wikidata KGQA pipeline using small fine-tuned models generates and executes SPARQL queries, beating GPT-4o on multi-hop and temporal benchmarks.
a is b” fail to learn “b is a
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
-
The benefits of query-based KGQA systems for complex and temporal questions in LLM era
A multi-stage Wikidata KGQA pipeline using small fine-tuned models generates and executes SPARQL queries, beating GPT-4o on multi-hop and temporal benchmarks.