Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor
Controlled text generation is very important for the practical use of language models because it ensures that the produced text includes only the desired attributes from a specific domain or dataset. Existing methods, however, are inapplicable to black-box models or suffer a significant trade-off between controlling the generated text and maintaining its fluency. This paper introduces the Score-based Progressive Editor (ScoPE), a novel approach designed to overcome these issues. ScoPE modifies the context at the token level during the generation process of a backbone language model. This modification guides the subsequent text to naturally include the target attributes. To facilitate this process, ScoPE employs a training objective that maximizes a target score, thoroughly considering both the ability to guide the text and its fluency. Experimental results on diverse controlled generation tasks demonstrate that ScoPE can effectively regulate the attributes of the generated text while fully utilizing the capability of the backbone large language models. Our codes are available at \url{https://github.com/ysw1021/ScoPE}.
Code (1)
Tasks
Language ModelingLanguage ModellingText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models
Recent work on controlled text generation has either required attribute-based fine-tuning of the base language model (LM), or has restricted the parameterization of the attribute discriminator to be compatible with the b…
AttributeLanguage ModelingLanguage ModellingText GenerationMix and Match: Learning-free Controllable Text Generation using Energy Language Models
Recent work on controlled text generation has either required attribute-based fine-tuning of the base language model (LM), or has restricted the parameterization of the attribute discriminator to be compatible with the b…
AttributeLanguage ModelingLanguage ModellingText GenerationMix and Match: Learning-free Controllable Text Generation using Energy Language Models
Due to the unidirectional nature of prevalent autoregressive generation models, recent work on controlled generation based on global text attributes has either required attribute-based fine-tuning of the base language mo…
AttributeLanguage ModelingLanguage ModellingText GenerationMix and Match: Learning-free Controllable Text Generationusing Energy Language Models
Due to the unidirectional nature of prevalent autoregressive generation models, recent work on controlled generation based on global text attributes has either required attribute-based fine-tuning of the base language mo…
AttributeLanguage ModelingLanguage ModellingStyle Transfer+1Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation
Many adversarial attack approaches are proposed to verify the vulnerability of language models. However, they require numerous queries and the information on the target model. Even black-box attack methods also require t…
Adversarial Attack