3 citations · 5 across the 5 of their papers we have counts for
5 papers · 1 filter
Preference-Guided Reflective Sampling for Aligning Language Models
Hai Ye, Hwee Tou Ng
Iterative data generation and model re-training can effectively align large language models(LLMs) to human preferences. The process of data sampling is crucial, as it significantly…
On the Robustness of Question Rewriting Systems to Questions of Varying Hardness
Hai Ye, Hwee Tou Ng, Wenjuan Han
In conversational question answering (CQA), the task of question rewriting~(QR) in context aims to rewrite a context-dependent question into an equivalent self-contained question t…
Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Hai Ye, Qizhe Xie, Hwee Tou Ng
In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation. To allow efficient adaptation, we cast th…
Test-Time Adaptation with Perturbation Consistency Learning
Yi Su, Yixin Ji, Juntao Li +2
Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios.…
Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
Hai Ye, Yuyang Ding, Juntao Li +1
A deployed question answering (QA) model can easily fail when the test data has a distribution shift compared to the training data. Robustness tuning (RT) methods have been widely…