A retrieval-augmented QA framework that synthesizes attributable Prolog modules from text chunks, retrieves Boolean predicates to build queries, and proactively asks users for missing facts, reported to beat a pure LLM RAG baseline on ShARC.
Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
A retrieval-augmented QA framework that synthesizes attributable Prolog modules from text chunks, retrieves Boolean predicates to build queries, and proactively asks users for missing facts, reported to beat a pure LLM RAG baseline on ShARC.