Metraipolis › archive › dc_dd9afaa86c08

Inferring Causal Relations between Two Sequences of Events with Language Models — arXiv:2609.39406

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39406
License (as archived)
CC0-1.0
Archived
2026-10-07T12:42:46.821Z
SHA-256 of the archived text
954c2409d456f781cd0d8d5c94cda4535c70a3b97b36dc7973b5b6552dd65d64
Stable URL of this page
https://metraipolis.com/documento/dc_dd9afaa86c08

How to cite

Inferring Causal Relations between Two Sequences of Events with Language Models — arXiv:2609.39406 — arXiv (en), https://arxiv.org/abs/2609.39406 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd9afaa86c08 (Metraipolis archive dc_dd9afaa86c08, sha256 954c2409d456f781cd0d8d5c94cda4535c70a3b97b36dc7973b5b6552dd65d64)
BibTeX
@misc{dcdd9afaa86c08,
  title = {Inferring Causal Relations between Two Sequences of Events with Language Models — arXiv:2609.39406},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39406},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd9afaa86c08; sha256 954c2409d456f781cd0d8d5c94cda4535c70a3b97b36dc7973b5b6552dd65d64},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39406. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Causal AI is a branch of Artificial Intelligence which helps understand and reason about cause and effect relationships, not just patterns or correlations. Causal discovery aims to infer elements of the underlying causal structure--often represented as a directed graph--from observational and, when available, interventional data. While causal discovery is the fundamental step for moving beyond mere associations toward genuine understanding, and thus the basic building block of causal AI, it becomes intrinsically difficult when causal relations must be inferred from single observations. In such situations, standard causal discovery methods cannot be used and one has to identify causal relations from limited amount of information. This is typically the case for, e.g., sequences of events produced by different alarms which need to be analyzed on the fly to detect abnormal phenomena, which are usually rare. We show in this study that it is possible to leverage the predictive power of Large Language Models (LLMs) to infer causal relations between only two sequences of events. This approach, which is validated on both synthetic and real data, provides better results than standard causal discovery algorithms on several time series data, even though these data were converted into smaller, single observed sequences.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.39406 — 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 2026-10-07T12:14:13.764Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).