按年被提到
20252025 · 2 次2026
大模型与语言模型›大模型评测与真实性·arXiv:2512.07796 · cs.AI

Large Causal Models from Large Language Models

Sridhar Mahadevan · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2025-12-27 · 最近 2026-01-08
3不同的人
2活跃月份
3讨论串
0被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We introduce a new paradigm for building large causal models (LCMs) that exploits the enormous potential latent in today's large language models (LLMs). We describe our ongoing experiments with an implemented system called DEMOCRITUS (Decentralized Extraction of Manifold Ontologies of Causal Relations Integrating Topos Universal Slices) aimed at building, organizing, and visualizing LCMs that span disparate domains extracted from carefully targeted textual queries to LLMs. DEMOCRITUS is methodologically distinct from traditional narrow domain and hypothesis centered causal inference that builds causal models from experiments that produce numerical data. A high-quality LLM is used to propose topics, generate causal questions, and extract plausible causal statements from a diverse range of domains. The technical challenge is then to take these isolated, fragmented, potentially ambiguous and possibly conflicting causal claims, and weave them into a coherent whole, converting them into relational causal triples and embedding them into a LCM. Addressing this technical challenge required inventing new categorical machine learning methods, which we can only briefly summarize in this paper, as it is focused more on the systems side of building DEMOCRITUS. We describe the implementation pipeline for DEMOCRITUS comprising of six modules, examine its computational cost profile to determine where the current bottlenecks in scaling the system to larger models. We describe the results of using DEMOCRITUS over a wide range of domains, spanning archaeology, biology, climate change, economics, medicine and technology. We discuss the limitations of the current DEMOCRITUS system, and outline directions for extending its capabilities.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论getnormality · 2026-01

“TLDR: This paper introduces a pipeline that extracts unstructured causal claims from LLMs and stitches them into a structured, geometric Large Causal Model. Traditional causal inference usually relies on numerical data from specific experiments. This paper instead proposes mining the latent world model inside an LLM. It prompts the model to generate caus…”

Large Causal Models from Large Language Models原评论 ↗
被提交为 story · 3 次