Using an LLM to induce an abstract rule from a query and then re-ranking retrieved rules with an LLM prompt improves rule retrieval and downstream reasoning in most tested configurations.
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
-
Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate
Using an LLM to induce an abstract rule from a query and then re-ranking retrieved rules with an LLM prompt improves rule retrieval and downstream reasoning in most tested configurations.