Large language models (LLMs) have achieved remarkable advancements in the
field of natural language processing. However, the sheer scale and
computational demands of these models present formidable challenges when
considering their practical deployment in resource-constrained contexts. While
techniques such as chain-of-thought (CoT) distillation have displayed promise
in distilling LLMs into small language models (SLMs), there is a risk that
distilled SLMs may still carry over flawed reasoning or hallucinations
inherited from their LLM counterparts. To address these issues, we propose a
twofold methodology: First, we introduce a novel method for distilling the
self-evaluation capability inherent in LLMs into SLMs, which aims to mitigate
the adverse effects of erroneous reasoning and reduce hallucinations. Second,
we advocate for a comprehensive distillation process that incorporates multiple
distinct chain-of-thought and self-evaluation paradigms and ensures a more
holistic and robust knowledge transfer into SLMs. Experiments on three NLP
benchmarks demonstrate that our method significantly improves the performance
of distilled SLMs and sheds light on the path towards developing smaller models
closely aligned with human cognition.

大型语言模型（LLMs）在自然语言处理领域取得了显著的进展，但是考虑到它们的规模和计算需求，将这些模型实际部署在资源受限的环境中面临着巨大的挑战。为了解决这些问题，我们提出了一种双重方法：首先，我们引入了一种将 LLMs 中固有的自我评价能力提取到 SLMs 中的新方法，旨在减少错误推理和幻觉的不利影响。其次，我们建议采用综合的蒸馏过程，结合多种不同的链式思维和自我评价范式，确保更全面、更稳健地将知识转移至 SLMs 中。在三个自然语言处理基准测试上进行的实验表明，我们的方法显著提高了蒸馏 SLMs 的性能，并为开发与人类认知更接近的较小模型指明了方向。