English

"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning

Computation and Language 2024-10-15 v4 Artificial Intelligence

Abstract

Personalized dialogue systems have gained significant attention in recent years for their ability to generate responses in alignment with different personas. However, most existing approaches rely on pre-defined personal profiles, which are not only time-consuming and labor-intensive to create but also lack flexibility. We propose In-Dialogue Learning (IDL), a fine-tuning framework that enhances the ability of pre-trained large language models to leverage dialogue history to characterize persona for completing personalized dialogue generation tasks without pre-defined profiles. Our experiments on three datasets demonstrate that IDL brings substantial improvements, with BLEU and ROUGE scores increasing by up to 200% and 247%, respectively. Additionally, the results of human evaluations further validate the efficacy of our proposed method.

Keywords

Cite

@article{arxiv.2403.03102,
  title  = {"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning},
  author = {Chuanqi Cheng and Quan Tu and Shuo Shang and Cunli Mao and Zhengtao Yu and Wei Wu and Rui Yan},
  journal= {arXiv preprint arXiv:2403.03102},
  year   = {2024}
}

Comments

Accepted by EMNLP 2024