# Interactive Classification by Asking Informative Questions

arXiv: https://arxiv.org/abs/1911.03598 · HTML: https://mlsanity.com/paper/1911.03598/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2019.

## Built on by (most cited first, 16 of 16)

- [Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs](https://mlsanity.com/paper/2311.09469/) (2023)
- [Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions](https://mlsanity.com/paper/2410.13788/) (2024)
- [Active Preference Inference using Language Models and Probabilistic Reasoning](https://mlsanity.com/paper/2312.12009/) (2023)
- [Open-domain clarification question generation without question examples](https://mlsanity.com/paper/2110.09779/) (2021)
- [CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval](https://mlsanity.com/paper/2405.15784/) (2024)
- [Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries](https://mlsanity.com/paper/2411.07237/) (2024)
- [InteractComp: Evaluating Search Agents With Ambiguous Queries](https://mlsanity.com/paper/2510.24668/) (2025)
- [Database Search Results Disambiguation for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2112.08351/) (2021)
- [Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People](https://mlsanity.com/paper/2510.20886/) (2025)
- [Closed-book Question Generation via Contrastive Learning](https://mlsanity.com/paper/2210.06781/) (2022)
- [Asking More Informative Questions for Grounded Retrieval](https://mlsanity.com/paper/2311.08584/) (2023)
- [MAPLE: A Framework for Active Preference Learning Guided by Large Language Models](https://mlsanity.com/paper/2412.07207/) (2024)
- [Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrieval](https://mlsanity.com/paper/2510.18659/) (2025)
- [LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information](https://mlsanity.com/paper/2609.30706/) (2026)
- [Neural Abstructions: Abstractions that Support Construction for Grounded Language Learning](https://mlsanity.com/paper/2107.09285/) (2021)
- [Which Questions Improve Learning the Most? Utility Estimation of Questions with LM-based Simulations](https://mlsanity.com/paper/2502.17383/) (2025)

## Abstract (arXiv)

We study the potential for interaction in natural language classification. We add a limited form of interaction for intent classification, where users provide an initial query using natural language, and the system asks for additional information using binary or multi-choice questions. At each turn, our system decides between asking the most informative question or making the final classification prediction.The simplicity of the model allows for bootstrapping of the system without interaction data, instead relying on simple crowdsourcing tasks. We evaluate our approach on two domains, showing the benefit of interaction and the advantage of learning to balance between asking additional questions and making the final prediction.