Control Prefixes for Parameter-Efficient Text Generation
Prefix-tuning is a powerful lightweight technique for adapting a large pre-trained language model to a downstream application. However, it uses the same dataset-level tuned prompt for all examples in the dataset. We extend this idea and propose a dynamic method, Control Prefixes, which allows for the inclusion of conditional input-dependent information, combining the benefits of prompt tuning and controlled generation. The method incorporates attribute-level learnable representations into different layers of a pre-trained transformer, allowing for the generated text to be guided in a particular direction. We provide a systematic evaluation of the technique and apply it to five datasets from the GEM benchmark for natural language generation (NLG). Although the aim is to develop a parameter-efficient model, we show Control Prefixes can even outperform full fine-tuning methods. We present state-of-the-art results on several data-to-text datasets, including WebNLG.
Code (2)
Tasks
Abstractive Text SummarizationAttributeData-to-Text GenerationLanguage ModelingLanguage ModellingText GenerationText SimplificationText SummarizationSimilar Papers 제목 키워드 기반
An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation
Recently, multi-aspect controllable text generation that controls the generated text in multiple aspects (e.g., sentiment, topic, and keywords) has attracted increasing attention. Although methods based on parameter effi…
Machine TranslationText GenerationTranslationControllable Natural Language Generation with Contrastive Prefixes
To guide the generation of large pretrained language models (LM), previous work has focused on directly fine-tuning the language model or utilizing an attribute discriminator. In this work, we propose a novel lightweight…
AttributeLanguage ModelingLanguage ModellingText GenerationControllable Natural Language Generation with Contrastive Prefixes
To guide the generation of large pretrained language models (LM), previous work has focused on directly fine-tuning the language model or utilizing an attribute discriminator. In this work, we propose a novel lightweight…
AttributeLanguage ModelingLanguage ModellingText GenerationLaPA$^2$: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation
Prefix-based methods have emerged as a promising paradigm for Controllable Text Generation (CTG) due to their parameter efficiency. However, while effective in short sequences, their controllability tends to diminish as …
Text GenerationPrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise
Natural Language Inference (NLI) models have been used in various ways to improve the factuality of LLM outputs. This is typically done by applying an NLI model to judge whether the model output is entailed from the supp…
Natural Language Inference