material
ID: qqp
Related Papers
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks
AbstractMany pairwise classification tasks, such as paraphrase detection and open-domain question answering, naturally have extreme label imbalance (e.g., 99.99% of examples are negatives). In contrast, many recent datasets heuristically choose …...
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level
Larger language models have higher accu- racy on average, but are they better on ev- ery single instance (datapoint)? Some work suggests larger models have higher out-of- distribution robustness, while …...
Increasing Robustness to Spurious Correlations using Forgettable Examples
AbstractNeural NLP models tend to rely on spurious correlations between labels and input features to perform their tasks. Minority examples, i.e., examples that contradict the spurious correlations present in the …...