指导性解码：指令微调的大型语言模型是从噪声指令中自我精炼的模型
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
AI总结：
本文提出指导性解码（ID）方法，通过对比原始指令与噪声指令的预测来调整 logits，无需额外参数更新即可显著提升指令微调模型在分布外指令下的性能。
摘要：
尽管指令微调的语言模型展现出了令人印象深刻的零样本泛化能力，但当面对训练集之外的指令时，这些模型往往难以生成准确的响应。本文提出了指导性解码（Instructive Decoding, ID），一种简单而有效的方法，用于增强指令微调模型的效能。具体而言，ID以对比方式调整下一个 token 预测的 logits，利用从原始指令的篡改版本（称为噪声指令）生成的预测。该噪声指令旨在引发可能偏离预期指令但仍然合理的响应。我们在一系列此类噪声指令上进行了实验，从通过随机单词插入语义噪声的指令，到诸如“opposite”等引发偏离响应的指令。我们的方法在各种指令微调模型和任务上取得了显著的性能提升，且无需任何额外的参数更新。值得注意的是，在 ID 中使用“opposite”作为噪声指令（其与原始指令表现出最大分歧），在多个模型和任务上持续产生最显著的性能提升。
英文摘要：
While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents Instructive Decoding (ID), a simple yet effective approach that augments the efficacy of instruction-tuned models. Specifically, ID adjusts the logits for next-token prediction in a contrastive manner, utilizing predictions generated from a manipulated version of the original instruction, referred to as a noisy instruction. This noisy instruction aims to elicit responses that could diverge from the intended instruction yet remain plausible. We conduct experiments across a spectrum of such noisy instructions, ranging from those that insert semantic noise via random words to others like 'opposite' that elicit the deviated responses. Our approach achieves considerable performance gains across various instruction-tuned models and tasks without necessitating any additional parameter updates. Notably, utilizing 'opposite' as the noisy instruction in ID, which exhibits the maximum divergence from the original instruction, consistently produces the most significant performance gains across multiple models and tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
