Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-
diversity problem when it comes to open-domain dialogue generation. As bland and generic …

Generating stylized responses is essential to build intelligent and engaging dialogue
systems. However, this task is far from well-explored due to the difficulties of rendering a …

Incorporating external knowledge into dialogue generation has been proven to benefit the
performance of an open-domain Dialogue System (DS), such as generating informative or …

Generating polite responses is essential to build intelligent and engaging dialogue systems.
However, this task is far from well-explored due to the difficulties of rendering a particular …

To maintain utterance quality of a persona-aware dialog system, inappropriate utterances for
the persona should be thoroughly filtered. When evaluating the appropriateness of a large …

As large language models (LLMs) become easily accessible nowadays, the trade-off
between safety and helpfulness can significantly impact user experience. A model that …

In recent years, latent variable models, such as the Conditional Variational Auto Encoder
(CVAE), have been applied to both personalized and empathetic dialogue generation. Prior …

Traditional recommender systems are usually single-shot systems, lacking real-time dialog
with customers. Using dialog as an interactive method can help capture user preferences …

Socially Intelligent Agents (SIAs) have become increasingly popular in various contexts,
including education and entertainment. However, creating complex social scenarios tailored …

Text generation aims to produce human-like natural language output for down-stream tasks.
It covers a wide range of applications like machine translation, document summarization …