小而有趣：一种反馈驱动的幽默蒸馏方法
Small But Funny: A Feedback-Driven Approach to Humor Distillation
AI总结：
本文提出反馈驱动的幽默蒸馏框架，让 LLM 同时担任教师与评论者，证明反馈比单纯模仿更能缩小 SLM 与大模型在幽默生成上的差距。
摘要：
大型语言模型（LLM）的出现展现出令人瞩目的语言生成能力，尤其是在执行复杂推理和创意写作等任务时。因此，通过模仿教师响应进行蒸馏，已成为将知识从 LLM 迁移到更易获取的小型语言模型（SLM）的流行技术。尽管这种方法在较简单的任务上效果良好，但在需要复杂语言理解和创造力的任务（如幽默生成）上仍存在显著的性能差距。我们假设，这一差距可能源于创意任务很难仅靠模仿来学习，并探索一种包含教师额外指导的方法是否能够带来更高性能。为解决该问题，我们研究了赋予 LLM 双重角色的效果：既作为生成数据的“教师”，也作为评估学生表现的“评论者”。我们在幽默生成上的实验表明，与仅依赖模仿相比，引入反馈显著缩小了 SLM 与其更大规模对应模型之间的性能差距。因此，本研究强调，在通过蒸馏迁移复杂语言能力时，将反馈作为数据之外的额外维度具有潜力。
英文摘要：
The emergence of Large Language Models (LLMs) has brought to light promising language generation capabilities, particularly in performing tasks like complex reasoning and creative writing. Consequently, distillation through imitation of teacher responses has emerged as a popular technique to transfer knowledge from LLMs to more accessible, Small Language Models (SLMs). While this works well for simpler tasks, there is a substantial performance gap on tasks requiring intricate language comprehension and creativity, such as humor generation. We hypothesize that this gap may stem from the fact that creative tasks might be hard to learn by imitation alone and explore whether an approach, involving supplementary guidance from the teacher, could yield higher performance. To address this, we study the effect of assigning a dual role to the LLM - as a "teacher" generating data, as well as a "critic" evaluating the student's performance. Our experiments on humor generation reveal that the incorporation of feedback significantly narrows the performance gap between SLMs and their larger counterparts compared to merely relying on imitation. As a result, our research highlights the potential of using feedback as an additional dimension to data when transferring complex language abilities via distillation.
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。
