English

Attribute Controlled Dialogue Prompting

Computation and Language 2023-07-12 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2307.05228,
  title  = {Attribute Controlled Dialogue Prompting},
  author = {Runcheng Liu and Ahmad Rashid and Ivan Kobyzev and Mehdi Rezagholizadeh and Pascal Poupart},
  journal= {arXiv preprint arXiv:2307.05228},
  year   = {2023}
}

Comments

Accepted at ACL 2023 In Findings

R2 v1 2026-06-28T11:27:04.188Z