KPT: keyword-guided pre-training for grounded dialog generation

Q Zhu, F Mi, Z Zhang, Y Wang, Y Li, X Jiang… - Proceedings of the …, 2023 - ojs.aaai.org
Incorporating external knowledge into the response generation process is essential to
building more helpful and reliable dialog agents. However, collecting knowledge-grounded …

Pan more gold from the sand: Refining open-domain dialogue training with noisy self-retrieval generation

Y Wang, Y Li, Y Wang, F Mi, P Zhou, X Wang… - arxiv preprint arxiv …, 2022 - arxiv.org
Real human conversation data are complicated, heterogeneous, and noisy, from which
building open-domain dialogue systems remains a challenging task. In fact, such dialogue …

Prompt Your Mind: Refine Personalized Text Prompts within Your Mind

G Su, Y Yang, J Guo - arxiv preprint arxiv:2311.05114, 2023 - arxiv.org
Large language models (LLMs) have demonstrated remarkable potential in natural
language understanding and generation, making them valuable tools for enhancing …