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

Why do large language models sometimes output factual inaccuracies and exhibit
erroneous reasoning? The brittleness of these models, particularly when executing long …

Large language models (LLMs) have gained widespread adoption in various natural
language processing tasks, including question answering and dialogue systems. However …

While large-scale neural language models, such as GPT2 and BART, have achieved
impressive results on various text generation tasks, they tend to get stuck in undesirable …

Develo** a successful dialogue policy for a multi-domain task-oriented dialogue (MDTD)
system is a challenging task. Basically, a desirable dialogue policy acts as the decision …

Generating desirable molecular structures in 3D is a fundamental problem for drug
discovery. Despite the considerable progress we have achieved, existing methods usually …

In this paper, we study the generation quality of interpolation-based retrieval-augmented
language models (LMs). These methods, best exemplified by the KNN-LM, interpolate the …

The standard paradigm of neural language generation adopts maximum likelihood
estimation (MLE) as the optimizing method. From a distributional view, MLE in fact minimizes …