English

Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective

Artificial Intelligence 2026-05-01 v1

Abstract

Compositional generalization tests are often used to estimate the compositionality of LLMs. However, such tests have the following limitations: (1) they only focus on the output results without considering LLMs' understanding of sample compositionality, resulting in explainability defects; (2) they rely on dataset partition to form the test set with combinations unseen in the training set, suffering from combination leakage issues. In this work, we propose a novel rule-generation perspective for compositionality estimation for LLMs. It requires LLMs to generate a program as rules for dataset mapping and provides estimates of the compositionality of LLMs using complexity-based theory. The perspective addresses the limitations of compositional generalization tests and provides a new way to analyze the compositionality characterization of LLMs. We conduct experiments and analysis of existing advanced LLMs based on this perspective on a string-to-grid task, and find various compositionality characterizations and compositionality deficiencies exhibited by LLMs.

Keywords

Cite

@article{arxiv.2604.27340,
  title  = {Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective},
  author = {Ziyao Xu and Cong Wang and Houfeng Wang},
  journal= {arXiv preprint arXiv:2604.27340},
  year   = {2026}
}

Comments

Accepted at ACL 2026 main conference

R2 v1 2026-07-01T12:42:46.435Z