Title |
|---|
 FlipGuard: Defending Preference Alignment against Update Regression with
Constrained OptimizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Pseudo-Label Training and Model Inertia in Neural Machine TranslationInternational Conference on Learning Representations (ICLR), 2023 |
 Improving Prediction Backward-Compatiblility in NLP Model Upgrade with
Gated FusionFindings (Findings), 2023 |
 Backward Compatibility During Data Updates by Weight InterpolationConference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 |
 ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent
TrainingIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 |
 Measuring and Reducing Model Update Regression in Structured Prediction
for NLPNeural Information Processing Systems (NeurIPS), 2022 |
