arxiv
PublishedJune 16, 2026 at 4:00 AM
Vernier: Probing Representational Misalignment Behind Lexical Gaps in Causal Reasoning
Publisher summary· verbatim
arXiv:2606.15733v1 Announce Type: cross Abstract: Instruction-tuned language models can answer the same causal-reasoning question differently after its English variable names are replaced by type-preserving placeholders, although the structural causal model and the gold answer are unchanged. We ask
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivTransformer-Based Inverse Microrheology for Experimental Mechanics at Ultra-High Strain Rates21harxivDeployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video21harxivSolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets21harxivForget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem21hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗