Redefining Proactivity for Information Seeking Dialogue
This addresses the limitation of reactive behavior in dialogue systems for users seeking sustained conversations, though it is incremental as it builds on existing proactive dialogue concepts.
The paper tackles the problem of information-seeking dialogue agents being predominantly reactive by proposing a new definition of proactivity focused on enhancing each response with new information related to the initial query. They constructed a dataset of 2,000 single-turn conversations and introduced Chain-of-Thought prompts that outperform standard prompts by up to 90% in zero-shot settings.
Information-Seeking Dialogue (ISD) agents aim to provide accurate responses to user queries. While proficient in directly addressing user queries, these agents, as well as LLMs in general, predominantly exhibit reactive behavior, lacking the ability to generate proactive responses that actively engage users in sustained conversations. However, existing definitions of proactive dialogue in this context do not focus on how each response actively engages the user and sustains the conversation. Hence, we present a new definition of proactivity that focuses on enhancing the `proactiveness' of each generated response via the introduction of new information related to the initial query. To this end, we construct a proactive dialogue dataset comprising 2,000 single-turn conversations, and introduce several automatic metrics to evaluate response `proactiveness' which achieved high correlation with human annotation. Additionally, we introduce two innovative Chain-of-Thought (CoT) prompts, the 3-step CoT and the 3-in-1 CoT prompts, which consistently outperform standard prompts by up to 90% in the zero-shot setting.