NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
Ranking
Overall
61
Content
70
Popularity
40
Observed public metrics from 1 member.
Merged summary
TL;DR - NeSy-RAG is a neuro-symbolic retrieval-augmented generation framework that converts retrieved text chunks into attributable Prolog modules, producing deterministic answers with verifiable execution traces. It matters because it addresses RAG's opacity problem while nearly doubling accuracy over a same-model baseline on ShARC.
- Each retrieved chunk is synthesized into semantically meaningful Prolog predicates encoding Boolean claims that may depend on user-specific facts.
- Joint natural language–code embeddings are used to retrieve predicates and compose them into executable Prolog queries.
- A symbolic knowledge-gap detection mechanism identifies missing user facts whose truth values change the query outcome and automatically triggers follow-up questions.
- On ShARC without domain-specific training, it reaches 61.1% accuracy vs. 42.8% for a same-model RAG baseline, with traces linking each reasoning step to its source.
Sources (1)
NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - NeSy-RAG is a neuro-symbolic retrieval-augmented generation framework that converts retrieved text chunks into attributable Prolog modules, producing deterministic answers with verifiable execution traces. It matters because it addresses RAG's opacity problem while nearly doubling accuracy over a same-model baseline on ShARC.
- Each retrieved chunk is synthesized into semantically meaningful Prolog predicates encoding Boolean claims that may depend on user-specific facts.
- Joint natural language–code embeddings are used to retrieve predicates and compose them into executable Prolog queries.
- A symbolic knowledge-gap detection mechanism identifies missing user facts whose truth values change the query outcome and automatically triggers follow-up questions.
- On ShARC without domain-specific training, it reaches 61.1% accuracy vs. 42.8% for a same-model RAG baseline, with traces linking each reasoning step to its source.