单调释义提升语言模型提示的泛化能力
Monotonic Paraphrasing Improves Generalization of Language Model Prompting
AI总结：
针对大语言模型性能受提示影响的问题，提出无需训练的单调释义策略MonoPara，通过融合双模型解码生成低困惑度提示，提升零样本提示性能与指令泛化能力。
摘要：
大语言模型（LLM）的性能可能会因同一任务的不同提示或指令而产生波动。学界普遍认为，导致这一现象的一个因素是模型对给定提示或指令的熟悉程度，通常用困惑度来衡量。然而，由于可能的提示短语空间极为庞大，找到困惑度最低的提示颇具挑战性。本文提出了单调释义（MonoPara），这是一种端到端解码策略，它通过融合用于提示（或指令）改写的释义语言模型与用于约束生成以降低困惑度的目标语言模型（即提示或指令的执行器），将给定的提示或指令改写为困惑度更低的版本。这种融合解码过程能够在不改变原提示语义的前提下高效完成释义，同时使目标语言模型计算出的每一代的困惑度单调下降。本文详细探究了贪心解码和基于搜索的解码两种MonoPara的可选解码方案。值得注意的是，MonoPara无需任何训练，且能单调降低改写后提示或指令的困惑度，在广泛的任务评估中提升了零样本语言模型提示的性能。此外，研究还表明MonoPara能有效提升语言模型在受扰动和未见过的任务指令上的泛化能力。
英文摘要：
Performance of large language models (LLMs) may vary with different prompts or instructions of even the same task. One commonly recognized factor for this phenomenon is the model's familiarity with the given prompt or instruction, which is typically estimated by its perplexity. However, finding the prompt with the lowest perplexity is challenging, given the enormous space of possible prompting phrases. In this paper, we propose monotonic paraphrasing (MonoPara), an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt (or instruction) rewriting, and a target LM (i.e. the prompt or instruction executor) that constrains the generation for lower perplexity. The ensemble decoding process can efficiently paraphrase the original prompt without altering its semantic meaning, while monotonically decreasing the perplexity of each generation as calculated by the target LM. We explore in detail both greedy and search-based decoding as two alternative decoding schemes of MonoPara. Notably, MonoPara does not require any training and can monotonically lower the perplexity of the paraphrased prompt or instruction, leading to improved performance of zero-shot LM prompting as evaluated on a wide selection of tasks. In addition, MonoPara is also shown to effectively improve LMs' generalization on perturbed and unseen task instructions.
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。
