no code implementations • 3 Apr 2024 • Xianlong Zeng, Fanghao Song, Ang Liu
This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs).
1 code implementation • 24 Jun 2021 • Xianlong Zeng, Fanghao Song, Zhongen Li, Krerkkiat Chusap, Chang Liu
Our method can be divided into three stages: 1) a neighborhood generation stage, which generates instances based on the given sample; 2) a classification stage, which yields classifications on the generated instances to carve out the local decision boundary and delineate the model behavior; and 3) a human-in-the-loop stage, which involves human to refine and explore the neighborhood of interest.
BIG-bench Machine Learning Explainable artificial intelligence +1