Metraipolis › archive › dc_a6718afe4df1

NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering — arXiv:2608.06292

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.06292
License (as archived): CC0-1.0
Archived: 2026-10-25T21:27:27.226Z
SHA-256 of the archived text: 9bd09eacefdb96c0b1fa65a0b22458cda1c6b11e8bf6135688e7f7b7706d3827
Stable URL of this page: https://metraipolis.com/documento/dc_a6718afe4df1

How to cite

NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering — arXiv:2608.06292 — arXiv (en), https://arxiv.org/abs/2608.06292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6718afe4df1 (Metraipolis archive dc_a6718afe4df1, sha256 9bd09eacefdb96c0b1fa65a0b22458cda1c6b11e8bf6135688e7f7b7706d3827)

BibTeX

@misc{dca6718afe4df1,
  title = {NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering — arXiv:2608.06292},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06292},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6718afe4df1; sha256 9bd09eacefdb96c0b1fa65a0b22458cda1c6b11e8bf6135688e7f7b7706d3827},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Symbolic Computation (cs.SC).
Pagina del lavoro: https://arxiv.org/abs/2608.06292 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T21:24:38.228Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).