RAR couples chain-of-thought reasoning with knowledge-graph-constrained path decoding and EM-style training, reporting 93.3 Hit@1 on WebQSP and 91.0 on CWQ.
InProceedings of the 62nd Annual Meeting of the Association for Computational Lin- guistics (Volume 1: Long Papers), pages 5014–5035, Bangkok, Thailand
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
-
Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQA
RAR couples chain-of-thought reasoning with knowledge-graph-constrained path decoding and EM-style training, reporting 93.3 Hit@1 on WebQSP and 91.0 on CWQ.