Metraipolis › archive › dc_ccf2dbf9680d

Generative Interpretability via Scalable Neuro-Symbolic Models — arXiv:2609.13529

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13529
License (as archived): CC0-1.0
Archived: 2026-10-15T22:48:34.726Z
SHA-256 of the archived text: 4225e461fe616d71b46461f9f0d6d3d56f3ad7f5342c65defd6eb38b371441a1
Stable URL of this page: https://metraipolis.com/documento/dc_ccf2dbf9680d

How to cite

Generative Interpretability via Scalable Neuro-Symbolic Models — arXiv:2609.13529 — arXiv (en), https://arxiv.org/abs/2609.13529 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccf2dbf9680d (Metraipolis archive dc_ccf2dbf9680d, sha256 4225e461fe616d71b46461f9f0d6d3d56f3ad7f5342c65defd6eb38b371441a1)

BibTeX

@misc{dcccf2dbf9680d,
  title = {Generative Interpretability via Scalable Neuro-Symbolic Models — arXiv:2609.13529},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13529},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccf2dbf9680d; sha256 4225e461fe616d71b46461f9f0d6d3d56f3ad7f5342c65defd6eb38b371441a1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13529. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As the use of Large Language Models moves from chatbots into agentic systems, where outputs become actions with irreversible consequences on reality, the existing paradigm on AI Interpretability research, post-hoc interpretability, is structurally inadequate for safe and trustworthy model deployment: it explains behavior after the fact but cannot audit or intervene in an inference computation before it commits to an output. We therefore argue for a shift toward \emph{generative interpretability}, an architectural property under which a model's inference pass natively exposes semantically meaningful checkpoints that are human-understandable and amenable to causal intervention. We show the merits of generative interpretability as comparison to other interpretability research paradigms, and propose Neuro-Symbolic Models as a concrete instantiation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Symbolic Computation (cs.SC).
Pagina del lavoro: https://arxiv.org/abs/2609.13529 — 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 2026-10-15T22:29:03.513Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).