finding
active
finding:scope-generalization-cot-boosts-2-digit-in-distribution-but-worsens-3-4-digit-oodScope generalization: CoT boosts 2-digit in-distribution but worsens 3-4 digit OOD
CoT increases dr for OOD operands.
Source paper
extracted_from(2025) · Edward Yi Chang · Kaya, Zeyneb N. · Ethan Chang
Neighborhood — ranked by edge-count
Communities (2)
community
- CoT effects on generalization, multimodal QA accuracy, and AI safety alignment training.
- Empirical studies showing CoT reasoning improves ID performance while harming OOD generalization, with probability calibration as a mitigation strategy.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Interpretation of scope generalization results
- Scope generalization results after LoRA+CoT fine-tuning
- Machine learning generalization when training and test distributions differ; linked to causal invariance.
- E2 finding showing CoT's limited benefit for OOD transfer, consistent with larger dr out of scope
- Generalization from 2-digit to 3-4 digit arithmetic; limited by mismatch dr.
- Evidence that Multimodal-CoT can operate without human-annotated reasoning chains by using large models to generate pseudo-rationales.
- Evidence that multimodal information accelerates convergence speed during training.
- Key geometry-to-behavior bridge finding in E3; robust to pooling choice, cosine vs. L2, and frozen external encoder