STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents
This addresses the issue of one-size-fits-all strategies limiting search effectiveness across diverse domains for conversational search engines, representing an incremental improvement in domain-specific transferability.
The paper tackles the problem of poor domain transferability in LLM-based conversational agents when asking clarification questions, introducing a novel method called Style that improves average search performance by ~10% on four unseen domains.
Equipping a conversational search engine with strategies regarding when to ask clarification questions is becoming increasingly important across various domains. Attributing to the context understanding capability of LLMs and their access to domain-specific sources of knowledge, LLM-based clarification strategies feature rapid transfer to various domains in a post-hoc manner. However, they still struggle to deliver promising performance on unseen domains, struggling to achieve effective domain transferability. We take the first step to investigate this issue and existing methods tend to produce one-size-fits-all strategies across diverse domains, limiting their search effectiveness. In response, we introduce a novel method, called Style, to achieve effective domain transferability. Our experimental results indicate that Style bears strong domain transferability, resulting in an average search performance improvement of ~10% on four unseen domains.