Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models

arXiv:2311.09214v2 Announce Type: replace
Abstract: Large language models (LLMs) have achieved remarkable advancements in natural language processing. However, the massive scale and computational demands of these models present formidable challenges when considering their practical deployment in resource-constrained environments. 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 inherit flawed reasoning and hallucinations from LLMs. To address these issues, we propose a twofold …

abstract arxiv capability challenges computational cs.cl deployment distillation environments evaluation however language language models language processing large language large language models llms massive mind natural natural language natural language processing practical processing scale thinking thought type