{"slug": "causal-modeling-of-adverse-pregnancy-outcomes-via-adaptive-llm-proposals", "title": "Causal Modeling of Adverse Pregnancy Outcomes via Adaptive LLM Proposals", "summary": "Researchers introduced a neurosymbolic framework that uses large language models (LLMs) as adaptive proposal distributions to generate causal hypotheses for adverse pregnancy outcomes (APOs), scoring them against empirical data. On a real-world clinical dataset, the method recovered all expert-validated edges in an expert-constructed causal graph and identified additional plausible causal relations, potentially offering new insights for targeted interventions.", "body_md": "arXiv:2608.21079v1 Announce Type: new\nAbstract: Adverse Pregnancy Outcomes (APOs) such as preterm birth and gestational diabetes can have long-term consequences for both the mother and child, yet an understanding of their causes remains elusive. Causal discovery in this domain is especially challenging due to a paucity of data and incomplete domain knowledge. As a result, pure data-driven methods fail, and Large Language Model (LLM) outputs remain inconsistent or contradictory. We introduce a neurosymbolic framework for generating plausible causal hypotheses that iteratively combines the broad prior knowledge of LLMs with empirical scoring on data. Our method treats the LLM as an adaptive proposal distribution, generating hypotheses that are scored against empirical data; the resulting high-scoring graphs are then used to update the LLM's context, steering subsequent generations toward more promising regions of the hypothesis space. We evaluate our approach on a real-world clinical dataset for modeling APOs and their risk factors, comparing our results against an expert-constructed causal graph. Our method recovers all expert-validated edges and identifies additional plausible causal relations not previously listed by experts, potentially providing new insights for targeted interventions.", "url": "https://wpnews.pro/news/causal-modeling-of-adverse-pregnancy-outcomes-via-adaptive-llm-proposals", "canonical_source": "https://www.machinebrief.com/news/causal-modeling-of-adverse-pregnancy-outcomes-via-adaptive-l-phl6", "published_at": "2026-08-24 04:00:00+00:00", "updated_at": "2026-08-24 05:14:03.157864+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/causal-modeling-of-adverse-pregnancy-outcomes-via-adaptive-llm-proposals", "markdown": "https://wpnews.pro/news/causal-modeling-of-adverse-pregnancy-outcomes-via-adaptive-llm-proposals.md", "text": "https://wpnews.pro/news/causal-modeling-of-adverse-pregnancy-outcomes-via-adaptive-llm-proposals.txt", "jsonld": "https://wpnews.pro/news/causal-modeling-of-adverse-pregnancy-outcomes-via-adaptive-llm-proposals.jsonld"}}