Answers are grounded in this paper and cite their sources.
This work studies out-of-distribution generalization, shortcut learning, and internal circuit routing in autoregressive Transformers using synthetic state-space benchmarks. By showing both behaviorally and mechanistically that sequence models can achieve 100% in-distribution accuracy and emit low-perplexity Chain-of-Thought rollouts while violating conservation invariants on out-of-distribution inputs, our results highlight the importance of causal circuit auditing and out-of-distribution verification in reliability-critical machine learning systems.
No takes yet. Share an insight, caveat, or question.
Shivansh Sharma (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: