Attribute Controlled Dialogue Prompting
This addresses the need for more flexible and efficient adaptation of large language models in open-domain dialogue tasks, though it is incremental over existing prompt-tuning methods.
The paper tackles the problem of fixed prompts in dialogue generation by developing an instance-specific prompt-tuning algorithm that generates prompts based on control codes, achieving performance comparable to fine-tuning with only 5%-6% of total parameters.
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 samples within a task, neglecting the fact that inputs vary greatly in some tasks such as open-domain dialogue generation. In this paper, we present a novel, instance-specific prompt-tuning algorithm for dialogue generation. Specifically, we generate prompts based on instance-level control code, rather than the conversation history, to explore their impact on controlled dialogue generation. Experiments on popular open-domain dialogue datasets, evaluated on both automated metrics and human evaluation, demonstrate that our method is superior to prompting baselines and comparable to fine-tuning with only 5%-6% of total parameters.