Back
Top 16%
11.0%
Top 0.4%
11.0%
Top 1.0%
10.2%
Top 2%
8.4%
Top 4%
6.0%
Top 0.8%
5.5%
Top 3%
5.5%
Top 3%
4.7%
Top 83%
4.7%
Top 4%
4.7%
Top 24%
4.7%
#1
3.6%
Top 6%
3.6%
Top 1.0%
1.8%
Top 4%
1.4%
Top 5%
1.4%
Top 6%
1.1%
Top 3%
0.9%
Top 5%
0.7%
Top 22%
0.7%
Top 5%
0.7%
An Information-Theoretic Perspective on Multi-LLM Uncertainty Estimation
2025-07-10
health informatics
Title + abstract only
View on medRxiv
Show abstract
Large language models (LLMs) often behave inconsistently across inputs, indicating uncertainty and motivating the need for its quantification in high-stakes settings. Prior work on calibration and uncertainty quantification often focuses on individual models, overlooking the potential of model diversity. We hypothesize that LLMs make complementary predictions due to differences in training and the Zipfian nature of language, and that aggregating their outputs leads to more reliable uncertainty e...
Predicted journal destinations
1
Scientific Reports
701 training papers
2
Journal of Biomedical Informatics
37 training papers
3
PLOS Digital Health
88 training papers
4
Journal of the American Medical Informatics Association
53 training papers
5
npj Digital Medicine
85 training papers
6
Computers in Biology and Medicine
39 training papers
7
JAMIA Open
35 training papers
8
BMC Medical Informatics and Decision Making
36 training papers
9
PLOS ONE
1737 training papers
10
PLOS Computational Biology
141 training papers
11
Nature Communications
483 training papers
12
Patterns
15 training papers
13
Journal of Medical Internet Research
81 training papers
14
Communications Medicine
63 training papers
15
JMIR Medical Informatics
16 training papers
16
International Journal of Medical Informatics
25 training papers
17
BMC Medical Research Methodology
41 training papers
18
Bioinformatics
24 training papers
19
Scientific Data
30 training papers
20
Nature Medicine
88 training papers
21
Frontiers in Digital Health
18 training papers