# Estimating the Usefulness of Clarifying Questions and Answers for Conversational Search

**Authors:** Ivan Sekulić, Weronika Łajewska, Krisztian Balog, Fabio Crestani  
**arXiv:** [2401.11463](https://arxiv.org/abs/2401.11463)  
**Date:** 2024-01-21  
**Summary page:** https://www.summarizepaper.com/en/paper/2401.11463v1/

## Key points

- Authors Ivan Sekulić, Weronika Łajewska, Krisztian Balog, and Fabio Crestani address the gap in research on processing and comprehension of users' answers to clarifying questions in conversational search systems.
- Existing literature primarily focuses on constructing clarifying questions with a scarcity of studies on handling user responses effectively.
- The authors propose a novel method involving a classifier to assess the usefulness of both prompted clarifying questions and user-provided answers.
- The key innovation is integrating valuable insights into conversation history and feeding them into a transformer-based query rewriting module.
- Results show significant enhancements over strong non-mixed-initiative baselines, demonstrating the effectiveness of their methodology.
- The technique can mitigate performance drops by selectively incorporating relevant information from user interactions to improve the overall conversational search experience.

## Summary

In their paper titled "Estimating the Usefulness of Clarifying Questions and Answers for Conversational Search," authors Ivan Sekulić, Weronika Łajewska, Krisztian Balog, and Fabio Crestani address the gap in research concerning the processing and comprehension of users' answers to clarifying questions in mixed-initiative conversational search systems. The study was presented at the 46th European Conference on Information Retrieval (ECIR '24) held in March 2024 in Glasgow, Scotland. The existing literature primarily focuses on constructing and generating clarifying questions; however, there is a scarcity of studies on effectively handling user responses to such queries. To fill this void, the authors propose a novel method that goes beyond simply appending answers to the original query. This approach could potentially degrade retrieval performance. The key innovation presented in this work is a classifier designed to assess the usefulness of both prompted clarifying questions and user-provided answers. By identifying valuable questions and responses, these insights are integrated into the conversation history and fed into a transformer-based query rewriting module. The results obtained from this approach demonstrate significant enhancements over strong non-mixed-initiative baselines, showcasing the effectiveness of their methodology. Moreover, one notable advantage of the proposed technique is its ability to mitigate performance drops when non-useful questions and answers are incorporated into the system. Through selectively incorporating relevant information gleaned from user interactions, the researchers have successfully improved the overall conversational search experience.