A survey of controllable text generation using transformer-based pre-trained language models
Controllable Text Generation (CTG) is an emerging area in the field of natural language
generation (NLG). It is regarded as crucial for the development of advanced text generation …
generation (NLG). It is regarded as crucial for the development of advanced text generation …
Controllable text generation for large language models: A survey
In Natural Language Processing (NLP), Large Language Models (LLMs) have demonstrated
high text generation quality. However, in real-world applications, LLMs must meet …
high text generation quality. However, in real-world applications, LLMs must meet …
Evaluating and inducing personality in pre-trained language models
Standardized and quantified evaluation of machine behaviors is a crux of understanding
LLMs. In this study, we draw inspiration from psychometric studies by leveraging human …
LLMs. In this study, we draw inspiration from psychometric studies by leveraging human …
Appdia: A discourse-aware transformer-based style transfer model for offensive social media conversations
Using style-transfer models to reduce offensiveness of social media comments can help
foster a more inclusive environment. However, there are no sizable datasets that contain …
foster a more inclusive environment. However, there are no sizable datasets that contain …
Whispering experts: Neural interventions for toxicity mitigation in language models
An important issue with Large Language Models (LLMs) is their undesired ability to
generate toxic language. In this work, we show that the neurons responsible for toxicity can …
generate toxic language. In this work, we show that the neurons responsible for toxicity can …
Few-shot table-to-text generation with prefix-controlled generator
Y Luo, M Lu, G Liu, S Wang - arxiv preprint arxiv:2208.10709, 2022 - arxiv.org
Neural table-to-text generation approaches are data-hungry, limiting their adaptation for low-
resource real-world applications. Previous works mostly resort to Pre-trained Language …
resource real-world applications. Previous works mostly resort to Pre-trained Language …
Medical reports summarization using text-to-text transformer
Summarization of medical reports in order to make them accessible to the large public is an
important task that can highly benefit from the recent emergence of the deep learning and …
important task that can highly benefit from the recent emergence of the deep learning and …
Computational storytelling and emotions: A survey
Storytelling has always been vital for human nature. From ancient times, humans have used
stories for several objectives including entertainment, advertisement, and education. Various …
stories for several objectives including entertainment, advertisement, and education. Various …
Plug-and-Play Controller for Story Completion: A Pilot Study toward Emotion-aware Story Writing Assistance
Emotions are essential for storytelling and narrative generation, and as such, the
relationship between stories and emotions has been extensively studied. The authors of this …
relationship between stories and emotions has been extensively studied. The authors of this …
Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs
Controlling the attribute intensity of text generation is crucial across scenarios (eg, writing
conciseness, chatting emotion, and explanation clarity). The remarkable capabilities of large …
conciseness, chatting emotion, and explanation clarity). The remarkable capabilities of large …