works on
benchmark 1large language models 1logical consistency 1reasoning evaluation 1reformulation testing 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Controlled Reformulation Testing for Logical Consistency in Large Language Models

Alexander Gu, Alan Chen

The paper introduces CRTBench, a benchmark of 350 question families to test whether large language models give consistent answers across controlled reformulations such as contrapos…