Papers by Yikai Zhou
Dissecting Human and LLM Preferences (2024.acl-long)
Copied to clipboard
| Challenge: | a recent study shows that human and Large Language Model preferences are important for model fine-tuning and evaluation. |
| Approach: | They dissect the preferences of human and 32 different Large Language Models to understand their quantitative composition. |
| Outcome: | The proposed model is compared with 32 different large language models using real-world user-model conversations. |
Self-Paced Learning for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that the training of neural machine translation (NMT) rely on the quality of artificial schedule drawn up with the handcrafted features, e.g. sentence length or word rarity. |
| Approach: | They propose to train NMT model using a self-paced learning approach that allows it to quantify the learning confidence over training examples and flexibly govern its learning via regulating the loss in each iteration step. |
| Outcome: | The proposed model outperforms baseline models and those trained with human-designed curricula on translation quality and convergence speed. |
Uncertainty-Aware Curriculum Learning for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has proven to be facilitated by curriculum learning which presents examples in an easy-to-hard order at different training stages. |
| Approach: | They propose to use an uncertainty-aware curriculum learning approach to assess data difficulty and model competence to provide examples in an easy-to-hard order at different training stages. |
| Outcome: | The proposed approach outperforms baseline and related methods on translation quality and convergence speed. |