MAP 并未消亡：通过条件化消除退化以揭示真实的语言模型众数
MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy
AI总结：
本文提出训练数据中少量低熵噪声会导致语言模型众数退化，并证明对长度等条件变量进行条件化的 MAP 解码能获得更流畅、更贴合主题的输出，且在 LLaMA-7B 上通过近似搜索无需微调即可产生合理结果。
摘要：
人们普遍观察到，自然语言生成（NLG）模型中的精确或近似 MAP（众数寻求）解码始终会导致退化输出（Holtzman et al., 2019; Stahlberg and Byrne, 2019）。先前的工作将这种行为归因于概率模型中众数存在根本且不可避免的不足，或语言建模中的弱点。与之相反，我们认为即使不存在任何建模误差，由于训练数据的污染，也可能出现退化众数。具体而言，我们认为即使将极少量的低熵噪声与总体文本分布混合，也会导致数据分布的众数变得退化。因此，我们提出将 MAP 解码应用于模型的真实条件分布，其中条件变量明确避免特定的退化行为。通过精确搜索，我们实证验证了机器翻译模型和语言模型的长度条件众数确实比其无条件众数更流畅且更贴合主题。我们还首次分享了来自这些模型以及 LLaMA-7B 模型的多个变体的许多精确众数序列示例。值得注意的是，我们观察到即使在 LLaMA-7B 的规模下，各种退化众数仍然存在。尽管我们无法用精确搜索在可处理范围内解决这些退化问题，但我们在未针对指令跟随进行训练的 LLaMA-7B 模型上执行了基于分类器的近似搜索，并发现无需任何微调即可获得合理的输出。
英文摘要：
It has been widely observed that exact or approximate MAP (mode-seeking) decoding from natural language generation (NLG) models consistently leads to degenerate outputs (Holtzman et al., 2019; Stahlberg and Byrne, 2019). Prior work has attributed this behavior to either a fundamental and unavoidable inadequacy of modes in probabilistic models or weaknesses in language modeling. Contrastingly, we argue that degenerate modes can even occur in the absence of any modeling error, due to contamination of the training data. Specifically, we argue that mixing even a tiny amount of low-entropy noise with a population text distribution can cause the data distribution's mode to become degenerate. We therefore propose to apply MAP decoding to the model's true conditional distribution where the conditioning variable explicitly avoids specific degenerate behavior. Using exact search, we empirically verify that the length-conditional modes of machine translation models and language models are indeed more fluent and topical than their unconditional modes. For the first time, we also share many examples of exact modal sequences from these models, and from several variants of the LLaMA-7B model. Notably, we observe that various kinds of degenerate modes persist, even at the scale of LLaMA-7B. Although we cannot tractably address these degeneracies with exact search, we perform a classifier-based approximate search on LLaMA-7B, a model which was not trained for instruction following, and find that we are able to elicit reasonable outputs without any finetuning.
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。
