Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models

arXiv:2404.00884v1 Announce Type: new
Abstract: Large language models (LLMs) have shown promising abilities of in-context learning (ICL), adapting swiftly to new tasks with only few-shot demonstrations. However, current few-shot methods heavily depend on high-quality, query-specific demos, which are often lacking. When faced with out-of-demonstration (OOD) queries, methods that rely on hand-crafted demos or external retrievers might fail. To bridge the gap between limited demos and OOD queries, we propose Self-Demos, a novel prompting method that elicits the inherent generalizability in …

abstract arxiv context cs.ai cs.cl current few-shot however in-context learning language language models large language large language models llms quality queries query tasks type