Table of Links
4 Results and 4.1 Increasing number of demonstrating examples
4.2 Impact of batching queries
A. Prompts used for ICL experiments
C. GPT4(V)-Turbo performance under many-shot ICL
D. Performance of many-shot ICL on medical QA tasks
Acknowledgments and Disclosure of Funding
B Prompt selection
We utilize a different set of prompts to test the robustness of ManyICL to differences in prompt wording. We randomly sample two datasets (HAM10000 and EuroSAT) for this experiment due to budget limit.
B.1 Prompts used for prompt selection experiments
Note that only the question section is shown here, and prompt 1 is used for all other image classification experiments.
B.1.1 Prompt 1
B.1.2 Prompt 2
B.1.3 Prompt 3
B.2 Prompt selection results
Figure 5 shows the sensitivity of performance to prompt selection on two datasets with three prompts. While there exists a small deviation in performance, but the overall log-linear improvement trend is consistent.
Authors:
(1) Yixing Jiang, Stanford University ([email protected]);
(2) Jeremy Irvin, Stanford University ([email protected]);
(3) Ji Hun Wang, Stanford University ([email protected]);
(4) Muhammad Ahmed Chaudhry, Stanford University ([email protected]);
(5) Jonathan H. Chen, Stanford University ([email protected]);
(6) Andrew Y. Ng, Stanford University ([email protected]).
This paper is
