# When in Doubt, Summon the Titans: Efficient Inference with Large Models

Source: [When in Doubt, Summon the Titans: Efficient Inference with Large Models](<https://www.sota2.com/research/paper/68fa6b0e1e209131cea2bc44>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:38:16.503Z

Authors: Ankit Singh Rawat, Manzil Zaheer, Aditya Krishna Menon, Amr Ahmed, Sanjiv Kumar

Published: 2021-10-19T22:56:49.000Z

## Abstract

Scaling neural networks to "large" sizes, with billions of parameters, has been shown to yield impressive results on many challenging problems. However, the inference cost incurred by such large models often prevents their application in most real-world settings. In this paper, we propose a two-stage framework based on distillation that realizes the modelling benefits of the large models, while largely preserving the computational benefits of inference with more lightweight models. In a nutshell, we use the large teacher models to guide the lightweight student models to only make correct predictions on a subset of "easy" examples; for the "hard" examples, we fall-back to the teacher. Such an approach allows us to efficiently employ large models in practical scenarios where easy examples are much more frequent than rare hard examples. Our proposed use of distillation to only handle easy instances allows for a more aggressive trade-off in the student size, thereby reducing the amortized cost of inference and achieving better accuracy than standard distillation. Empirically, we demonstrate the benefits of our approach on both image classification and natural language processing benchmarks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2110.10305>)

[PDF](<https://arxiv.org/pdf/2110.10305.pdf>)
