Exploring ReAct Prompting for Task-Oriented Dialogue: Insights and Shortcomings
This work addresses improving user experience in task-oriented dialogue systems, but it is incremental as it adapts an existing prompting method to a new domain with mixed results.
The authors applied the ReAct prompting strategy to task-oriented dialogue using LLMs, finding that while it underperformed in simulation success rates compared to SOTA, human evaluations showed less difference and higher subjective satisfaction due to more natural responses.
Large language models (LLMs) gained immense popularity due to their impressive capabilities in unstructured conversations. Empowering LLMs with advanced prompting strategies such as reasoning and acting (ReAct) (Yao et al., 2022) has shown promise in solving complex tasks traditionally requiring reinforcement learning. In this work, we apply the ReAct strategy to guide LLMs performing task-oriented dialogue (TOD). We evaluate ReAct-based LLMs (ReAct-LLMs) both in simulation and with real users. While ReAct-LLMs severely underperform state-of-the-art approaches on success rate in simulation, this difference becomes less pronounced in human evaluation. Moreover, compared to the baseline, humans report higher subjective satisfaction with ReAct-LLM despite its lower success rate, most likely thanks to its natural and confidently phrased responses.