Metraipolis › archive › dc_b42b9efda5dc

Auto-Formalizing Neuro-Symbolic Predictors — arXiv:2610.01519

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01519
License (as archived)
CC0-1.0
Archived
2026-10-06T12:14:05.686Z
SHA-256 of the archived text
6d35d948d74fea97fcecfbabb8125fae1d79c6469a6b3a3a8f42a7e4c17f8bd2
Stable URL of this page
https://metraipolis.com/documento/dc_b42b9efda5dc

How to cite

Auto-Formalizing Neuro-Symbolic Predictors — arXiv:2610.01519 — arXiv (en), https://arxiv.org/abs/2610.01519 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b42b9efda5dc (Metraipolis archive dc_b42b9efda5dc, sha256 6d35d948d74fea97fcecfbabb8125fae1d79c6469a6b3a3a8f42a7e4c17f8bd2)
BibTeX
@misc{dcb42b9efda5dc,
  title = {Auto-Formalizing Neuro-Symbolic Predictors — arXiv:2610.01519},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01519},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b42b9efda5dc; sha256 6d35d948d74fea97fcecfbabb8125fae1d79c6469a6b3a3a8f42a7e4c17f8bd2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01519. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified constraints, making them particularly suitable for high-stakes applications where compliance with domain knowledge is essential. A key bottleneck in this paradigm is the acquisition of symbolic constraints: encoding domain knowledge into logical formulas remains a manual and expert-intensive process. In this work, we investigate the extent to which auto-formalization via LLMs can systematically translate textual knowledge into symbolic knowledge that can be plugged into NeSy predictors. To this end, we introduce auto-nesy-bench, a new benchmark for evaluating constraint formalization and its impact on downstream accuracy of NeSy predictors. Through an extensive evaluation across several domains, we find that LLMs can formalize constraints to a meaningful extent, generating formulas that are often similar to those provided by human experts. Moreover, when the generated formulas are syntactically valid, they can lead to high-quality downstream predictions. The code and benchmark are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.01519 — 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 2026-10-06T10:21:28.191Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).