# NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering

arXiv: https://arxiv.org/abs/2608.06292 · HTML: https://mlsanity.com/paper/2608.06292/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 10 of 10)

- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Interpretation of Natural Language Rules in Conversational Machine Reading](https://mlsanity.com/paper/1809.01494/) (2018)
- [Reliable Reasoning Beyond Natural Language](https://mlsanity.com/paper/2407.11373/) (2024)
- [Efficient Code Embeddings from Code Generation Models](https://mlsanity.com/paper/2508.21290/) (2025)
- [ProSLM : A Prolog Synergized Language Model for explainable Domain Specific Knowledge Based Question Answering](https://mlsanity.com/paper/2409.11589/) (2024)
- [Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading](https://mlsanity.com/paper/2310.13409/) (2023)

## Built on by (most cited first, 1 of 1)

- [PAGR: Proof-Carrying Algebraic-Geometric Retrieval: A Quiver-, Provenance-, and Sheaf-Theoretic Framework for Grounded LLM Retrieval](https://mlsanity.com/paper/2609.06127/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. However, its reasoning process remains largely opaque: intermediate reasoning steps are difficult to verify and cannot be reliably attributed to specific evidence. Moreover, missing user-specific context is rarely detected systematically, often leading to incomplete or incorrect output. We propose NeSy-RAG, a modular neuro-symbolic RAG framework that synthesizes attributable Prolog modules from retrieved text chunks. For each chunk, the system generates semantically meaningful predicates that encode Boolean claims, which may depend on user facts. Using joint natural language-code embeddings, predicates are retrieved and composed into Prolog queries. To address incomplete user context, we introduce a symbolic knowledge-gap detection mechanism that identifies missing user facts whose truth values affect the query outcome and automatically triggers follow-up interactions. Executing the resulting Prolog queries yields deterministic answers together with transparent execution traces that link each reasoning step to its originating source. On the ShARC benchmark, without domain-specific training, NeSy-RAG achieves 61.1% accuracy, outperforming a same-model RAG baseline that achieves 42.8% accuracy.