Back
Top 0.4%
17.6%
Top 0.3%
11.7%
#1
10.9%
Top 1%
9.3%
Top 2%
6.4%
Top 3%
6.4%
Top 38%
6.4%
Top 2%
5.9%
Top 86%
3.8%
Top 2%
2.8%
Top 4%
1.9%
Top 2%
1.9%
Top 43%
1.5%
Top 3%
1.5%
Top 2%
0.9%
Top 4%
0.7%
Top 55%
0.7%
Top 4%
0.7%
Top 31%
0.7%
ARCADE: Enhancing Automated Document Analysis Through Adversarial Multi-Agent Validation
2025-12-23
health informatics
Title + abstract only
View on medRxiv
Show abstract
We present ARCADE (Adversarial Critique Architecture for Document Evaluation), a multi-agent architecture addressing three limitations of traditional retrieval-augmented generation for automated document analysis: incomplete information extraction, shallow analytical depth, and framework paraphrasing. We compared ARCADE against Single-Pass RAG using 95 policy documents (50 National Cancer Control Plans and 45 Cardiovascular Disease plans) evaluated on 36 metrics across six capabilities: Natural ...
Predicted journal destinations
1
Journal of the American Medical Informatics Association
53 training papers
2
Journal of Biomedical Informatics
37 training papers
3
JAMIA Open
35 training papers
4
npj Digital Medicine
85 training papers
5
Journal of Medical Internet Research
81 training papers
6
PLOS Digital Health
88 training papers
7
Scientific Reports
701 training papers
8
BMC Medical Informatics and Decision Making
36 training papers
9
PLOS ONE
1737 training papers
10
International Journal of Medical Informatics
25 training papers
11
Computers in Biology and Medicine
39 training papers
12
JMIR Medical Informatics
16 training papers
13
Nature Communications
483 training papers
14
BMC Medical Research Methodology
41 training papers
15
Patterns
15 training papers
16
Scientific Data
30 training papers
17
eLife
262 training papers
18
Frontiers in Digital Health
18 training papers
19
JAMA Network Open
125 training papers