downstream performance

Delving into the Reversal Curse: How Far Can Large Language Models Generalize? NeurIPS 2024 Downstream Trade-offs of a Family of Text Watermarks EMNLP 2024 Exploring Correlations of Self-Supervised Tasks for Graphs ICML 2024 Perfect Alignment May be Poisonous to Graph Contrastive Learning ICML 2024 Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance ACL 2024 Does the Correctness of Factual Knowledge Matter for Factual Knowledge-Enhanced Pre-trained Language Models? EMNLP 2023 Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale. ACL 2023 How does the task complexity of masked pretraining objectives affect downstream performance? ACL 2023 On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training NeurIPS 2023 RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank ICML 2023 Will Large-scale Generative Models Corrupt Future Datasets? ICCV 2023 Do More Negative Samples Necessarily Hurt In Contrastive Learning? ICML 2022 Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning NAACL 2022 How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns NAACL 2022 Investigating the Role of Negatives in Contrastive Representation Learning AISTATS 2022 Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora ACL 2022 On the Impact of Data Augmentation on Downstream Performance in Natural Language Processing ACL 2022 On the Downstream Performance of Compressed Word Embeddings NeurIPS 2019