Dynamic Contexts for Generating Suggestion Questions in RAG Based Conversational Systems
This work addresses a specific usability issue for users of RAG-based conversational systems, but it is incremental as it builds on existing prompting techniques.
The paper tackled the problem of users struggling to craft effective queries for RAG-based conversational agents by developing a suggestion question generator using dynamic contexts, and showed that this approach generates better suggestion questions compared to other prompting methods.
When interacting with Retrieval-Augmented Generation (RAG)-based conversational agents, the users must carefully craft their queries to be understood correctly. Yet, understanding the system's capabilities can be challenging for the users, leading to ambiguous questions that necessitate further clarification. This work aims to bridge the gap by developing a suggestion question generator. To generate suggestion questions, our approach involves utilizing dynamic context, which includes both dynamic few-shot examples and dynamically retrieved contexts. Through experiments, we show that the dynamic contexts approach can generate better suggestion questions as compared to other prompting approaches.