Papers by Bum Chul Kwon
Finspector: A Human-Centered Visual Inspection Tool for Exploring and Comparing Biases among Foundation Models (2023.acl-demo)
Copied to clipboard
| Challenge: | Existing pre-trained transformer-based language models have shown exceptional performance on various benchmarks, but hidden biases can be found within these models. |
| Approach: | They propose a human-centered visual inspection tool to detect biases in different categories through log-likelihood scores generated by language models. |
| Outcome: | The proposed tool detects biases in different categories through log-likelihood scores generated by language models. |