Zobrazeno 1 - 10
of 167
pro vyhledávání: '"Ng, Hwee Tou"'
Autor:
Ye, Hai, Ng, Hwee Tou
Pre-trained large language models (LLMs) can be tailored to adhere to human instructions through instruction tuning. However, due to shifts in the distribution of test-time data, they may not always execute instructions accurately, potentially genera
Externí odkaz:
http://arxiv.org/abs/2409.00935
Autor:
Ye, Hai, Ng, Hwee Tou
Large language models (LLMs) are aligned with human preferences by reinforcement learning from human feedback (RLHF). Effective data sampling is crucial for RLHF, as it determines the efficiency of model training, ensuring that models learn from the
Externí odkaz:
http://arxiv.org/abs/2408.12163
Knowledge in the real world is being updated constantly. However, it is costly to frequently update large language models (LLMs). Therefore, it is crucial for LLMs to understand the concept of temporal knowledge. However, prior works on temporal ques
Externí odkaz:
http://arxiv.org/abs/2311.09821
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 that gives the same answer. In this paper, we are interested in the rob
Externí odkaz:
http://arxiv.org/abs/2311.06807
Autor:
Qorib, Muhammad Reza, Ng, Hwee Tou
Quality estimation models have been developed to assess the corrections made by grammatical error correction (GEC) models when the reference or gold-standard corrections are not available. An ideal quality estimator can be utilized to combine the out
Externí odkaz:
http://arxiv.org/abs/2310.14947
Relation extraction (RE) aims to extract relations from sentences and documents. Existing relation extraction models typically rely on supervised machine learning. However, recent studies showed that many RE datasets are incompletely annotated. This
Externí odkaz:
http://arxiv.org/abs/2306.09697
Reasoning about time is of fundamental importance. Many facts are time-dependent. For example, athletes change teams from time to time, and different government officials are elected periodically. Previous time-dependent question answering (QA) datas
Externí odkaz:
http://arxiv.org/abs/2306.08952
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 the problem as a stochastic decision-making process, aiming to determine
Externí odkaz:
http://arxiv.org/abs/2306.06779
Large language models (LLMs) have made significant progress in natural language processing (NLP), and are utilized extensively in various applications. Recent works, such as chain-of-thought (CoT), have shown that intermediate reasoning steps can imp
Externí odkaz:
http://arxiv.org/abs/2305.15014
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 studied to enhance model robustness against distribution shifts before
Externí odkaz:
http://arxiv.org/abs/2302.04618