English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large Language Models (LLMs) have made remarkable strides in various tasks.Whether LLMs are competitive few-shot solvers for information extraction (IE)tasks, however, remains an open problem. In this work, we aim to provide athorough answer to this question. Through extensive experiments on ninedatasets across four IE tasks, we demonstrate that current advanced LLMsconsistently exhibit inferior performance, higher latency, and increased budgetrequirements compared to fine-tuned SLMs under most settings. Therefore, weconclude that LLMs are not effective few-shot information extractors ingeneral. Nonetheless, we illustrate that with appropriate prompting strategies,LLMs can effectively complement SLMs and tackle challenging samples that SLMsstruggle with. And moreover, we propose an adaptive filter-then-rerank paradigmto combine the strengths of LLMs and SLMs. In this paradigm, SLMs serve asfilters and LLMs serve as rerankers. By prompting LLMs to rerank a smallportion of difficult samples identified by SLMs, our preliminary systemconsistently achieves promising improvements (2.4% F1-gain on average) onvarious IE tasks, with an acceptable time and cost investment.

Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!