GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
Inserts optimizable latent states at a chosen transformer layer and directly differentiates continuation-token log-probabilities through them at test time, improving accuracy over chain-of-thought while yielding token-level gradient attributions that show latent influence concentrating on reasoning-connector tokens.
Why it matters
22 upvotes on HuggingFace Daily Papers; reports 64.5% average accuracy across five backbones and three reasoning benchmarks, beating CoT prompting by 6.6 points.
Importance: 2/5
Concrete quantitative gains on an interpretable latent-reasoning method.
Sources
official
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
official
Paper page - GradCuit