We explore incorporating natural language inference (NLI) into the text generative pipeline by using a pre-trained NLI model to assess whether a generated sentence entails, contradicts, or is neutral to the prompt and preceding text. First, we show that the NLI task is predictive of generation errors made by GPT-3. We use these results to develop an NLI-informed generation procedure for GPT-J. Then, we evaluate these generations by obtaining human annotations on error types and overall quality. We find that an NLI strategy of maximizing entailment improves text generation when the nucleus sampling randomness parameter value is high, while one which maximizes contradiction is in fact productive when the parameter value is low. Overall, though, we demonstrate that an NLI strategy of maximizing the neutral class provides the highest quality of generated text (significantly better than the vanilla generations), regardless of parameter value.

翻译：我们探索将自然语言推理（NLI）融入文本生成流程，通过使用预训练的NLI模型评估生成句子是否蕴含、矛盾或中立于提示文本及前文。首先，我们证明NLI任务能够预测GPT-3的生成错误。基于此结果，我们开发了NLI引导的GPT-J生成流程。随后，通过人工标注错误类型与整体质量评估这些生成结果。研究发现，当核采样随机参数值较高时，最大化蕴含的NLI策略能提升文本生成质量；而当参数值较低时，最大化矛盾的策略反而有效。但总体而言，我们证明了无论参数值如何，最大化中立类别的NLI策略能产生最高质量的生成文本（显著优于标准生成结果）。