# An Analysis of Mixed Initiative and Collaboration in Information-Seeking Dialogues

arXiv: https://arxiv.org/abs/2005.12340 · HTML: https://mlsanity.com/paper/2005.12340/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

## Built on by (most cited first, 8 of 8)

- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversations](https://mlsanity.com/paper/2305.10172/) (2023)
- [Semi-Supervised Variational Reasoning for Medical Dialogue Generation](https://mlsanity.com/paper/2105.06071/) (2021)
- [Evaluating Generative Ad Hoc Information Retrieval](https://mlsanity.com/paper/2311.04694/) (2023)
- [Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search](https://mlsanity.com/paper/2402.07742/) (2024)
- [Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation](https://mlsanity.com/paper/2609.03727/) (2026)
- [Mix-Initiative Response Generation with Dynamic Prefix Tuning](https://mlsanity.com/paper/2403.17636/) (2024)
- [Do Images Clarify? A Study on the Effect of Images on Clarifying Questions in Conversational Search](https://mlsanity.com/paper/2602.08700/) (2026)

## Abstract (arXiv)

The ability to engage in mixed-initiative interaction is one of the core requirements for a conversational search system. How to achieve this is poorly understood. We propose a set of unsupervised metrics, termed ConversationShape, that highlights the role each of the conversation participants plays by comparing the distribution of vocabulary and utterance types. Using ConversationShape as a lens, we take a closer look at several conversational search datasets and compare them with other dialogue datasets to better understand the types of dialogue interaction they represent, either driven by the information seeker or the assistant. We discover that deviations from the ConversationShape of a human-human dialogue of the same type is predictive of the quality of a human-machine dialogue.