Open-world survival games pose significant challenges for AI algorithms ...
Pre-trained large language models (LLMs) capture procedural knowledge ab...
Like people, LLMs do not always generate the best text for a given gener...
Pretrained large language models have become indispensable for solving
v...
Social bias in Pretrained Language Models (PLMs) affects text generation...
Labeling social-media data for custom dimensions of toxicity and social ...
Parameter efficient learning methods (PERMs) have recently gained signif...
Closed-book question answering (QA) requires a model to directly answer ...
Existing knowledge-grounded dialogue systems typically use finetuned ver...
Pretrained general-purpose language models can achieve state-of-the-art
...
Detecting social bias in text is challenging due to nuance, subjectivity...
Document grounded generation is the task of using the information provid...
Recent work in natural language processing (NLP) has focused on ethical
...
Neural controllable text generation is an important area gaining attenti...
Sentence ordering is the task of arranging the sentences of a given text...
This paper introduces a new task of politeness transfer which involves
c...
Dialogue research tends to distinguish between chit-chat and goal-orient...
Dialogue research tends to distinguish between chit-chat and goal-orient...
With the rapid growth of e-Commerce, online product search has emerged a...
Procedurally generating cohesive and interesting game environments is
ch...
We critique recent work on ethics in natural language processing. Those
...
Visual storytelling is the task of generating stories based on a sequenc...
Recent work in neural generation has attracted significant interest in
c...
We describe the setting and results of the ConvAI2 NeurIPS competition t...
This paper introduces a document grounded dataset for text conversations...
Style transfer is the task of transferring an attribute of a sentence (e...
Style transfer is the task of rephrasing the text to contain specific
st...
There has been a long standing interest in understanding `Social Influen...