Large language models (LLMs) effectively generate fluent text when the t...
Prompt-based methods with large pre-trained language models (PLMs) have ...
Training dialogue systems often entails dealing with noisy training exam...
Training accurate intent classifiers requires labeled data, which can be...
Collecting data for training dialog systems can be extremely expensive d...
Crowdsourcing platforms are often used to collect datasets for training ...
Practical dialogue systems require robust methods of detecting out-of-sc...
Existing goal-oriented dialogue datasets focus mainly on identifying slo...
We introduce SocialIQa, the first large-scale benchmark for commonsense
...
We consider negotiation settings in which two agents use natural languag...