CLIFT: Analysing Natural Distribution Shift on Question Answering Models in Clinical Domain
This addresses the need for robustness in clinical AI models under distribution shifts, though it is incremental as it primarily provides a benchmark.
The paper tackles the problem of natural distribution shift in clinical domain question answering by introducing CLIFT, a testbed with 7.5k samples, and finds that model performance degrades on new test sets despite strong original results.
This paper introduces a new testbed CLIFT (Clinical Shift) for the clinical domain Question-answering task. The testbed includes 7.5k high-quality question answering samples to provide a diverse and reliable benchmark. We performed a comprehensive experimental study and evaluated several QA deep-learning models under the proposed testbed. Despite impressive results on the original test set, the performance degrades when applied to new test sets, which shows the distribution shift. Our findings emphasize the need for and the potential for increasing the robustness of clinical domain models under distributional shifts. The testbed offers one way to track progress in that direction. It also highlights the necessity of adopting evaluation metrics that consider robustness to natural distribution shifts. We plan to expand the corpus by adding more samples and model results. The full paper and the updated benchmark are available at github.com/openlifescience-ai/clift