Related papers: Discourse-Aware Soft Prompting for Text Generation

Fine-tuning is the de facto way to leverage large pretrained language models to perform downstream tasks. However, it modifies all the language model parameters and therefore necessitates storing a full copy for each task. In this paper, we…

Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning…

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks. For example, one popular method, prefix-tuning, prepends trainable tokens to sequences while freezing the…

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…

Conditional natural language generation methods often require either expensive fine-tuning or training a large language model from scratch. Both are unlikely to lead to good results without a substantial amount of data and computational…

Recently, prefix-tuning has gained increasing attention as a parameter-efficient finetuning method for large-scale pretrained language models. The method keeps the pretrained models fixed and only updates the prefix token parameters for…

Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data…

Response generation is one of the critical components in task-oriented dialog systems. Existing studies have shown that large pre-trained language models can be adapted to this task. The typical paradigm of adapting such extremely large…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

Prototype-driven text generation uses non-parametric models that first choose from a library of sentence "prototypes" and then modify the prototype to generate the output text. While effective, these methods are inefficient at test time as…

Many real-world applications require making multiple predictions from the same text. Fine-tuning a large pre-trained language model for each downstream task causes computational burdens in the inference time due to several times of forward…

Syntactically controlled paraphrase generation requires language models to generate paraphrases for sentences according to specific syntactic structures. Existing fine-tuning methods for this task are costly as all the parameters of the…

Few-shot abstractive summarization has become a challenging task in natural language generation. To support it, we designed a novel soft prompts architecture coupled with a prompt pre-training plus fine-tuning paradigm that is effective and…

Existing knowledge-grounded conversation systems generate responses typically in a retrieve-then-generate manner. They require a large knowledge base and a strong knowledge retrieval component, which is time- and resource-consuming. In this…

Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task…

The large language models have achieved superior performance on various natural language tasks. One major drawback of such approaches is they are resource-intensive in fine-tuning new datasets. Soft-prompt tuning presents a…

We present a novel natural language generation system for spoken dialogue systems capable of entraining (adapting) to users' way of speaking, providing contextually appropriate responses. The generator is based on recurrent neural networks…

In a controllable text generation dataset, there exist unannotated attributes that could provide irrelevant learning signals to models that use it for training and thus degrade their performance. We propose focused prefix tuning(FPT) to…

Despite the remarkable generative capabilities of language models in producing naturalistic language, their effectiveness on explicit manipulation and generation of linguistic structures remain understudied. In this paper, we investigate…

Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation. Despite the success in modeling intra-sentence coherence, existing generation models…