PrOntoQA

https://github.com/asaparov/prontoqa/ @article{saparov2022language, title={Language models are greedy reasoners: A systematic formal analysis of chain-of-thought}, author={Saparov, Abulhair and He, He}, journal={arXiv preprint arXiv:2210.01240}, year={2022} }

Papers using PrOntoQA (2)

Interventional Grounding Audits: Black-Box Premise-Dependency Tests for LLM Chain-of-Thought via Predicate Substitution2026Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training2025