Papers by Kazuaki Furumai
Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval (2024.findings-emnlp)
Copied to clipboard
Kazuaki Furumai, Roberto Legaspi, Julio Romero, Yudai Yamazaki, Yasutaka Nishimura, Sina Semnani, Kazushi Ikeda, Weiyan Shi, Monica Lam
| Challenge: | Existing methods to improve persuasive chatbots use only a handful of predefined strategies. |
| Approach: | They propose a persuasive chatbot based on large language models that is factual and more persuasive by leveraging many more nuanced strategies. |
| Outcome: | The proposed chatbot is factual and more persuasive by leveraging many more nuanced strategies. |