Papers with metamorphic testing
MATO: A Model-Agnostic Training Optimization for Aspect Sentiment Triplet Extraction (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing models with strong in-house performance may struggle to generalize to diverse expressions. |
| Approach: | They propose a model-agnostic t**raining method to improve ASTE model inference . they propose to compute the violation rate (VR) on each element of one triplet . |
| Outcome: | The proposed method can improve aspect sentiment triplet extraction models consistent with expected results facing triplet element diversity. |
SALTED: A Framework for SAlient Long-tail Translation Error Detection (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Traditional machine translation metrics are insensitive to the long tail of behavioral problems. |
| Approach: | They propose a specification-based framework for behavioral testing of NMT models . they use high-precision detectors that flag errors between a source sentence and output . |
| Outcome: | The proposed framework provides a reliable view of problems that were previously invisible. |