Deep Shah

Google

Google Research

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Inference & Quantization (1)Reasoning & Chain-of-Thought (1)Training Efficiency & Optimization (1)

Frequent co-authors

Sanket Badhe (1)Sanket Badhe (1)Deep Shah (1)

Papers (1)

Feb 24, 2026

Google Research2w ago

Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning

Forget fine-tuning: Prompt-Level Distillation lets small models match frontier reasoning performance by distilling explicit reasoning patterns into structured system prompts.

Sanket Badhe, Sanket Badhe, Deep Shah +1

Inference & Quantization Reasoning & Chain-of-Thought Training Efficiency & Optimization

Search

Deep Shah

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)