EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding
This addresses data scarcity in LLMs for downstream tasks, offering an incremental improvement over existing methods.
The paper tackles the problem of limited annotated data for large language models by introducing EpiCoDe, a method that boosts performance without extra training, achieving significant and robust improvements across three tasks and four models.
The remarkable performance of Large language models (LLMs) relies heavily on the availability of abundant high-quality training data. However, the high cost of acquiring annotated data often prevents models from obtaining capabilities to tackle downstream tasks. In this paper, we introduce a novel method, EpiCoDe that boosts model performance in data-scarcity scenarios without extra training. We first employ model extrapolation to enhance a finetuned model with its inferior version, and then adopt contrastive decoding to further reduce predicted errors, by comparing the logit scores given by the extrapolated and the vanilla finetuned model. Experiments across three tasks over four different LLMs show that EpiCoDe consistently outperforms existing methods with significant and robust improvement. We also propose a new theoretical framework to reveal the mechanism behind contrastive decoding in data-scarcity scenarios, which further helps us better understand the effectiveness of EpiCoDe.