AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction

Jiabang He, Lei Wang, Yi Hu, Ning Liu, Hui Liu, Xing Xu, Heng Tao Shen

ICCV 2023 · Large language models › Language, safety and interpretability · approach: In-context learning analysis · 48 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add hard demonstrations (ablation)ICL-D3IE (Davinci-003) · FUNSD (ID)entity F1: 78.20 -> 90.32Improved
add layout-aware demonstrations (ablation)ICL-D3IE (Davinci-003) · CORD (ID)entity F1: 84.13 -> 94.12Improved
add layout-aware demonstrations (ablation)ICL-D3IE (Davinci-003) · SROIE (ID)entity F1: 96.83 -> 97.88No clear effect
add label mapping (ablation)ICL-D3IE (Davinci-003) · CORD (ID)entity F1: 87.94 -> 94.12Improved
add formatting demonstrations (ablation)ICL-D3IE (Davinci-003) · SROIE (ID)entity F1: 90.58 -> 97.88Improved
add formatting demonstrations (ablation)ICL-D3IE (Davinci-003) · CORD (ID)entity F1: 93.07 -> 94.12Improved
use ICL-D3IE instead of standard ICLDavinci-003 · FUNSD (ID)entity F1: 71.52 -> 90.32Improved
ICL-D3IE vs fully fine-tuned LayoutLMv3 on OOD text perturbationsICL-D3IE (Davinci-003) · CORD (OOD)entity F1: 75.23 -> 91.23Improved
ICL-D3IE vs fully fine-tuned LayoutLMv3 on ID CORDICL-D3IE (Davinci-003) · CORD (ID)entity F1: 96.56 -> 94.12Hurt
use ChatGPT instead of Davinci-003 as backboneICL-D3IE · CORD (ID)entity F1: 94.12 -> 87.13Hurt
order demonstrations M-H-L-F instead of M-L-H-F (ablation)ICL-D3IE (Davinci-003) · FUNSD, CORD, SROIEentity F1Improved
update hard demonstrations iteratively (up to 20 iterations) (ablation)ICL-D3IE (Davinci-003) · FUNSD, CORD, SROIEentity F1Improved

Later papers that compared with this method

1 later accepted paper reports ICL-D3IE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy