Orthogonal rotation primes LLM reasoning, boosting accuracy on 30 of 32 benchmarks
Rotate2Think shows that hidden states during reasoning form a distinct, tightly clustered direction separate from input embeddings. By estimating a rotation via orthogonal Procrustes from a few solved examples and injecting the rotated vector at inference, it lifts accuracy in 30 of 32 model‑benchmark combos across math, science, code, and even multimodal tasks.