Metraipolis › archive › dc_dba8213db850

xWhyL: Causal Interactive Learning — arXiv:2609.26037

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26037
License (as archived)
CC0-1.0
Archived
2026-10-08T13:46:51.083Z
SHA-256 of the archived text
c98a4f80dba2933c6a712044b3d6018d14a28190eaeec5e3ac2f2f965f0a5df9
Stable URL of this page
https://metraipolis.com/documento/dc_dba8213db850

How to cite

xWhyL: Causal Interactive Learning — arXiv:2609.26037 — arXiv (en), https://arxiv.org/abs/2609.26037 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dba8213db850 (Metraipolis archive dc_dba8213db850, sha256 c98a4f80dba2933c6a712044b3d6018d14a28190eaeec5e3ac2f2f965f0a5df9)
BibTeX
@misc{dcdba8213db850,
  title = {xWhyL: Causal Interactive Learning — arXiv:2609.26037},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26037},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dba8213db850; sha256 c98a4f80dba2933c6a712044b3d6018d14a28190eaeec5e3ac2f2f965f0a5df9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26037. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Explanations are central to causal reasoning, and cognitive science has long established that the human drive to explain is itself a mechanism for learning about causality. Despite this, learning from those abductive signals is largely ignored in artificial intelligence. While explainable AI (XAI) increasingly draws on causal models to generate explanations, the converse direction about what explanations can do for causality remains largely unexplored. To fill this gap, we propose xWhyL, a formal framework connecting causality and XAI by learning causal models from explanations. We develop a mathematical theory that translates explanations into a learning signal complementary to observational data, and demonstrate how it enables overcoming the limits of observational causal discovery. As explanations can be derived from incorrect beliefs and clash with data, a tension we call the Causal Tug-of-War, we prove conditions under which our framework rejects misspecified explanations rather than absorbing them. Our practical instantiation, Causal Interactive Learning (CIL), shows how expert explanations can efficiently support causal discovery and distinguish correct from incorrect explanations.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.26037 — 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 2026-10-08T13:18:38.278Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).