Squad Optimized Span Classification With Confidence Scoring

via “squad v2 benchmark-aligned answer span prediction”

question-answering model by undefined. 1,85,194 downloads.

Unique: Trained on SQuAD v2's 50k unanswerable questions (vs. SQuAD v1 which had only answerable questions), exposing the model to negative examples where the answer is not in the passage, improving robustness to out-of-distribution queries

vs others: Achieves ~88-90 F1 on SQuAD v2 dev set (competitive with BERT-large baseline); better calibrated confidence scores than SQuAD v1-only models due to unanswerable question exposure