Compositional Causal Reasoning Evaluation in Language Models

2025/03/06 by Maasch, Jacqueline R. M. A., Hüyük, Alihan, Xu, Xinnuo +2 · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2503.04556

Abstract

Causal reasoning and compositional reasoning are two core aspirations in AI. Measuring the extent of these behaviors requires principled evaluation methods. We explore a unified perspective that considers both behaviors simultaneously, termed compositional causal reasoning (CCR): the ability to infer how causal measures compose and, equivalently, how causal quantities propagate through graphs. We instantiate a framework for the systematic evaluation of CCR for the average treatment effect and the probability of necessity and sufficiency. As proof of concept, we demonstrate CCR evaluation for language models in the LLama, Phi, and GPT families. On a math word problem, our framework revealed a range of taxonomically distinct error patterns. CCR errors increased with the complexity of causal paths for all models except o1.

Cited by

• CausalARC: Abstract Reasoning with Causal World Models

Related

• CLadder: Assessing Causal Reasoning in Language Models
• Causal Evaluation of Language Models
• CausalEval: Towards Better Causal Reasoning in Language Models
• CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models
• Is Knowledge All Large Language Models Needed for Causal Reasoning?