使用大型语言模型进行非因果文本生成的最优词序：西班牙语案例
Optimal word order for non-causal text generation with Large Language Models: the Spanish case
AI总结：
本文针对单向因果LLM可能不适应自由词序语言的问题，提出基于Viterbi算法的最大似然词序估计方法，并通过西班牙语实验比较非因果与因果生成顺序。
摘要：
自然语言生成（NLG）的普及得益于具有零样本推理能力的大型语言模型（LLM）的进步。然而，大多数神经系统采用仅解码器的因果（单向）transformer模型，这类模型对英语很有效，但可能会降低词序不那么严格、存在主语省略或关系从句挂靠偏好不同的语言的丰富性。这是首个从分析角度处理非因果语言模型最优文本生成顺序的工作。我们提出了一种基于Viterbi算法的新方法，用于最大似然词序估计。我们分析了西班牙语NLG的非因果最大似然顺序概率，随后分析了用西班牙语因果NLG生成相同短语的概率。这一比较分析表明，因果NLG更偏好类似英语的SVO结构。我们还使用Spearman等级相关分析了最优生成顺序与因果从左到右生成顺序之间的关系。结果表明，最大似然估计器预测的理想顺序与因果顺序并不密切相关，并且可能受到目标句句法结构的影响。
英文摘要：
Natural Language Generation (NLG) popularity has increased owing to the progress in Large Language Models (LLMs), with zero-shot inference capabilities. However, most neural systems utilize decoder-only causal (unidirectional) transformer models, which are effective for English but may reduce the richness of languages with less strict word order, subject omission, or different relative clause attachment preferences. This is the first work that analytically addresses optimal text generation order for non-causal language models. We present a novel Viterbi algorithm-based methodology for maximum likelihood word order estimation. We analyze the non-causal most-likelihood order probability for NLG in Spanish and, then, the probability of generating the same phrases with Spanish causal NLG. This comparative analysis reveals that causal NLG prefers English-like SVO structures. We also analyze the relationship between optimal generation order and causal left-to-right generation order using Spearman's rank correlation. Our results demonstrate that the ideal order predicted by the maximum likelihood estimator is not closely related to the causal order and may be influenced by the syntactic structure of the target sentence.
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。
