无需额外训练，通过外推与对比解码提升小样本场景下的模型性能。
EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding
- 利用模型外推融合优劣版本，增强微调模型能力。
- 对比解码显著降低预测误差，跨任务平均提升12.3%。
- 理论分析揭示机制，适合资源受限场景的模型优化。
大型语言模型（LLMs）的优异表现依赖于大量高质量训练数据，但标注数据成本高昂，常导致模型无法有效应对下游任务。本文提出EpiCoDe方法，在不增加训练的前提下，通过模型外推将微调后的模型与其低版本结合，并采用对比解码，比较外推模型与原始微调模型的对数概率输出，进一步减少预测错误。在四种不同LLM上对三个任务的实验表明，EpiCoDe始终优于现有方法，提升显著且稳健。此外，我们提出了新的理论框架，揭示了对比解码在数据稀缺场景下的作用机制，深化了对EpiCoDe有效性的理解。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。