Abstract
Contrastive decoding is a lightweight and effective inference-time method that improves the quality of text generation in Large Language Models. However, algorithms such as DoLa (Decoding by Contrastive Layers) have only been implemented in decoder-only architectures and studied for their impact on improving factuality. This work adapts DoLa for the T5 and FLAN-T5 model families and evaluates its impact on the models' instruction following capabilities, which to our knowledge is the first implementation of a contrastive decoding strategy in an encoder-decoder architecture. Our results show that DoLa improves the faithfulness of text generation for certain categories of tasks and harms others. To understand these results, we present a layer-by-layer analysis of logit evolution in a FLAN-T5 model to quantify DoLa's impact on token output probabilities.
Abstract (translated)
对比解码是一种轻量且有效的方法，可以在推理阶段提升大型语言模型生成文本的质量。然而，如DoLa（通过对比层进行解码）等算法仅在解码器架构中实现，并主要用于研究其对提高事实性的影响。这项工作将DoLa适应到T5和FLAN-T5模型家族，并评估它对这些模型遵循指令能力的影响。据我们所知，这是首次在编码器-解码器架构中实施对比解码策略。我们的结果表明，DoLa对于某些任务类别能够提升文本生成的忠实度，但同时也会损害其他类别的性能。为了理解这一现象，我们在FLAN-T5模型中的每一层进行了对数几率演化分析，以量化DoLa对令牌输出概率的影响。
URL
https://arxiv.org/abs/2512.03803
