Causal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization

• URL: http://arxiv.org/abs/2509.12387v1
• Date: Mon, 15 Sep 2025 19:28:09 GMT
• Title: Causal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization
• Abstract summary: We introduce Causal-Symbolic Meta-Learning, a novel framework that learns to infer the latent causal structure of a task distribution.<n>By meta-learning a shared causal world model across a distribution of tasks, CSML can rapidly adapt to novel tasks.<n>Our experiments show that CSML dramatically outperforms state-of-the-art meta-learning and neuro-symbolic baselines.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern deep learning models excel at pattern recognition but remain fundamentally limited by their reliance on spurious correlations, leading to poor generalization and a demand for massive datasets. We argue that a key ingredient for human-like intelligence-robust, sample-efficient learning-stems from an understanding of causal mechanisms. In this work, we introduce Causal-Symbolic Meta-Learning (CSML), a novel framework that learns to infer the latent causal structure of a task distribution. CSML comprises three key modules: a perception module that maps raw inputs to disentangled symbolic representations; a differentiable causal induction module that discovers the underlying causal graph governing these symbols and a graph-based reasoning module that leverages this graph to make predictions. By meta-learning a shared causal world model across a distribution of tasks, CSML can rapidly adapt to novel tasks, including those requiring reasoning about interventions and counterfactuals, from only a handful of examples. We introduce CausalWorld, a new physics-based benchmark designed to test these capabilities. Our experiments show that CSML dramatically outperforms state-of-the-art meta-learning and neuro-symbolic baselines, particularly on tasks demanding true causal inference.

Related papers

• SLASH the Sink: Sharpening Structural Attention Inside LLMs [55.75072688988806]
  Large Language Models (LLMs) show remarkable semantic understanding but struggle with structural understanding when processing graph topologies in a serialized format.<n>We propose StructuraL Attention SHarpening (SLASH), which amplifies this internal structural understanding via a plug-and-play attention redistribution.
  arXiv  Detail & Related papers  (2026-05-11T12:59:07Z)
• How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns [51.02752099869218]
  Large Language Models (LLMs) display strikingly different generalization behaviors.<n>We introduce a novel benchmark that decomposes reasoning into atomic core skills.<n>We show that RL-tuned models maintain more stable behavioral profiles and resist collapse in reasoning skills, whereas SFT models exhibit sharper drift and overfit to surface patterns.
  arXiv  Detail & Related papers  (2025-12-30T08:16:20Z)
• Foundation Model for Skeleton-Based Human Action Understanding [56.89025287217221]
  This paper presents a Unified Skeleton-based Dense Representation Learning framework.<n>USDRL consists of a Transformer-based Dense Spatio-Temporal (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT)
  arXiv  Detail & Related papers  (2025-08-18T02:42:16Z)
• Inducing Causal World Models in LLMs for Zero-Shot Physical Reasoning [7.4149859076511815]
  Causal World Model Induction (CWMI) is a framework designed to embed an explicit model of causal physics within an AI system.<n>CWMI significantly outperforms state-of-the-art AI systems on zero-shot physical reasoning tasks.
  arXiv  Detail & Related papers  (2025-07-26T08:08:26Z)
• Failure Modes of LLMs for Causal Reasoning on Narratives [51.19592551510628]
  We investigate the interaction between world knowledge and logical reasoning.<n>We find that state-of-the-art large language models (LLMs) often rely on superficial generalizations.<n>We show that simple reformulations of the task can elicit more robust reasoning behavior.
  arXiv  Detail & Related papers  (2024-10-31T12:48:58Z)
• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models [42.17166746027585]
  We introduce a bidirectional weighted graph-based framework to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $beta$-VAE based module to extract factors as the initial nodes of the graph. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement.
  arXiv  Detail & Related papers  (2024-07-26T15:32:21Z)
• Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment [10.814585613336778]
  Causal representation learning aims to combine the core strengths of machine learning and causality. This thesis investigates what is possible for CRL without direct supervision, and thus contributes to its theoretical foundations.
  arXiv  Detail & Related papers  (2024-06-19T09:14:40Z)
• Can Large Language Models Learn Independent Causal Mechanisms? [9.274428418715347]
  Large Language Models (LLMs) fall short on the same tasks in uncommon settings or with distribution shifts. We show that causal models, that learn abstract variables and causal relationships, can demonstrate increased robustness against changes in the distribution.
  arXiv  Detail & Related papers  (2024-02-04T23:04:02Z)
• Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph [26.361815957385417]
  This study introduces a novel solution, HG-SCM (Heterogeneous Graph as Structural Causal Model) It can mimic the human perception and decision process through two key steps: constructing intelligible variables based on semantics derived from the graph schema and automatically learning task-level causal relationships among these variables by incorporating advanced causal discovery techniques. HG-SCM achieved the highest average performance rank with minimal standard deviation, substantiating its effectiveness and superiority in terms of both predictive power and generalizability.
  arXiv  Detail & Related papers  (2023-12-10T04:34:35Z)
• Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
  We propose to expose captured knowledge in the form of a directed acyclic causal graph. We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-09-30T20:59:42Z)
• On the Generalization and Adaption Performance of Causal Models [99.64022680811281]
  Differentiable causal discovery has proposed to factorize the data generating process into a set of modules. We study the generalization and adaption performance of such modular neural causal models. Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes.
  arXiv  Detail & Related papers  (2022-06-09T17:12:32Z)
• Relating Graph Neural Networks to Structural Causal Models [17.276657786213015]
  Causality can be described in terms of a structural causal model (SCM) that carries information on the variables of interest and their mechanistic relations. We present a theoretical analysis that establishes a novel connection between GNN and SCM. We then establish a new model class for GNN-based causal inference that is necessary and sufficient for causal effect identification.
  arXiv  Detail & Related papers  (2021-09-09T11:16:31Z)
• Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning [76.00395335702572]
  A central goal for AI and causality is the joint discovery of abstract representations and causal structure. Existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs. In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them.
  arXiv  Detail & Related papers  (2021-07-02T05:44:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.