CEV-LM: Controlled Edit Vector Language Model for Shaping Natural Language Generations

arXiv:2402.14290v1 Announce Type: cross
Abstract: As large-scale language models become the standard for text generation, there is a greater need to tailor the generations to be more or less concise, targeted, and informative, depending on the audience/application. Existing control approaches primarily adjust the semantic (e.g., emotion, topics), structural (e.g., syntax tree, parts-of-speech), and lexical (e.g., keyword/phrase inclusion) properties of text, but are insufficient to accomplish complex objectives such as pacing which control the complexity and readability of the text. In …

abstract application arxiv audience become control cs.cl cs.lg edit emotion language language model language models natural natural language scale semantic standard text text generation topics type vector