Metraipolis › archive › dc_628c7c42e508

Causally Fair Generation with Large Language Models — arXiv:2610.04444

Source
arXiv
Original
https://arxiv.org/abs/2610.04444
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:33.822Z
SHA-256 of the archived text
53d6ed4ab84347710ff9fa15298083c1339614440dfe1412996c73249af7d8d1
Stable URL of this page
https://metraipolis.com/documento/dc_628c7c42e508

How to cite

Causally Fair Generation with Large Language Models — arXiv:2610.04444 — arXiv, https://arxiv.org/abs/2610.04444 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_628c7c42e508 (Metraipolis archive dc_628c7c42e508, sha256 53d6ed4ab84347710ff9fa15298083c1339614440dfe1412996c73249af7d8d1)
BibTeX
@misc{dc628c7c42e508,
  title = {Causally Fair Generation with Large Language Models — arXiv:2610.04444},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04444},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_628c7c42e508; sha256 53d6ed4ab84347710ff9fa15298083c1339614440dfe1412996c73249af7d8d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04444. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) are increasingly used to generate, complete, and transform information in settings where their outputs can shape consequential decisions, raising concerns about their impact on demographic disparities. In this context, causal inference provides a principled basis for assessing fairness, because it attributes observed disparities to the mechanisms that generated them, which a purely statistical approach cannot do even with infinite data. In LLM generation, a query may request several causally related variables, each of which is both an outcome of interest and a possible cause of other outputs, and the information supplied in the prompt need not follow a topological or a temporal order. This calls for methods that can analyze and selectively remove disparities from such a flexible generation process. In this paper we introduce Causally Fair Generation with LLMs (CFG, for short). CFG extracts relevant concepts, grounds generation in a reference population and causal diagram, and removes user-selected causal effects. CFG also allows pathways deemed justifiable for the task's utility to be retained, which is known in legal literature as business necessity. Further, we provide formal guarantees for our method when eliminating all discriminatory causal effects in the adapted population model, under appropriate causal assumptions. We evaluate CFG with four LLMs in three real-world settings based on population data and on a synthetic dataset with a known causal ground truth.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.04444 — 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 2026-10-06T05:24:05.472Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).