Natural Language Generation (NLG) has improved exponentially in recent years thanks to
the development of sequence-to-sequence deep learning technologies such as Transformer …

Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

Recently developed large language models have achieved remarkable success in
generating fluent and coherent text. However, these models often tend to'hallucinate'which …

Natural Language Generation (NLG) has made great progress in recent years due to the
development of deep learning techniques such as pre-trained language models. This …

Low-frequency word prediction remains a challenge in modern neural machine translation
(NMT) systems. Recent adaptive training methods promote the output of infrequent words by …

We conducted a survey of 135 software engineering (SE) practitioners to understand how
they use Generative AI-based chatbots like ChatGPT for SE tasks. We find that they want to …

The Neural Machine Translation (NMT) model is essentially a joint language model
conditioned on both the source sentence and partial translation. Therefore, the NMT model …

High quality end-to-end speech translation model relies on a large scale of speech-to-text
training data, which is usually scarce or even unavailable for some low-resource language …

Non-autoregressive neural machine translation (NAT) suffers from the multi-modality
problem: the source sentence may have multiple correct translations, but the loss function is …

Attention mechanisms have achieved substantial improvements in neural machine
translation by dynamically selecting relevant inputs for different predictions. However, recent …