Large Language Models (LLMs) have made remarkable strides in various tasks. However, whether they are competitive few-shot solvers for information extraction (IE) tasks and surpass fine-tuned small Pre-trained Language Models (SLMs) remains an open problem. This paper aims to provide a thorough answer to this problem, and moreover, to explore an approach towards effective and economical IE systems that combine the strengths of LLMs and SLMs. Through extensive experiments on eight datasets across three IE tasks, we show that LLMs are not effective few-shot information extractors in general, given their unsatisfactory performance in most settings and the high latency and budget requirements. However, we demonstrate that LLMs can well complement SLMs and effectively solve hard samples that SLMs struggle with. Building on these findings, we propose an adaptive filter-then-rerank paradigm, in which SLMs act as filters and LLMs act as rerankers. By utilizing LLMs to rerank a small portion of difficult samples identified by SLMs, our preliminary system consistently achieves promising improvements (2.1% F1-gain on average) on various IE tasks, with acceptable cost of time and money.

翻译：大型语言模型（LLMs）在各类任务中取得了显著进展。然而，它们是否能成为信息抽取（IE）任务中具有竞争力的小样本求解器，并超越经过微调的小型预训练语言模型（SLMs），仍是一个待解决的问题。本文旨在对此问题提供全面解答，并进一步探索一种结合LLMs与SLMs优势的高效且经济的信息抽取系统方案。通过在三个IE任务的八个数据集上进行广泛实验，我们表明，LLMs在大多数设定下表现不佳，且存在高延迟和预算需求，因此通常并非有效的小样本信息抽取器。然而，我们证明LLMs能很好地补充SLMs，有效解决SLMs难以处理的硬样本。基于这些发现，我们提出了一种自适应过滤-重排序范式，其中SLMs充当过滤器，LLMs充当重排序器。通过利用LLMs对SLMs识别出的少量困难样本进行重排序，我们的初步系统在各种IE任务上持续取得可观的改进（平均F1值提升2.1%），且时间和金钱成本可接受。