# Zero-Shot and Efficient Clarification Need Prediction in Conversational Search

arXiv: https://arxiv.org/abs/2503.00179 · HTML: https://mlsanity.com/paper/2503.00179/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 53 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Builds on (most cited first, 30 of 35)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [Asking Clarifying Questions in Open-Domain Information-Seeking Conversations](https://mlsanity.com/paper/1907.06554/) (2019)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models](https://mlsanity.com/paper/2212.07769/) (2022)
- [ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback](https://mlsanity.com/paper/2210.12329/) (2022)
- [Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions](https://mlsanity.com/paper/2109.05794/) (2021)
- [Ask-before-Plan: Proactive Language Agents for Real-World Planning](https://mlsanity.com/paper/2406.12639/) (2024)
- [Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training](https://mlsanity.com/paper/2406.00222/) (2024)
- [CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models](https://mlsanity.com/paper/2405.12063/) (2024)
- [PACIFIC: Towards Proactive Conversational Question Answering over Tabular and Textual Data in Finance](https://mlsanity.com/paper/2210.08817/) (2022)
- [Towards LLM-guided Causal Explainability for Black-box Text Classifiers](https://mlsanity.com/paper/2309.13340/) (2023)
- [Conversational Information Seeking](https://mlsanity.com/paper/2201.08808/) (2022)
- [DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation](https://mlsanity.com/paper/2202.12350/) (2022)
- [MIMICS: A Large-Scale Data Collection for Search Clarification](https://mlsanity.com/paper/2006.10174/) (2020)
- [CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation](https://mlsanity.com/paper/2210.04873/) (2022)
- [RefNet: A Reference-aware Network for Background Based Conversation](https://mlsanity.com/paper/1908.06449/) (2019)
- [Ranked List Truncation for Large Language Model-based Re-Ranking](https://mlsanity.com/paper/2404.18185/) (2024)
- [Query Performance Prediction using Relevance Judgments Generated by Large Language Models](https://mlsanity.com/paper/2404.01012/) (2024)
- [Zero-shot Clarifying Question Generation for Conversational Search](https://mlsanity.com/paper/2301.12660/) (2023)
- [Generating Usage-related Questions for Preference Elicitation in Conversational Recommender Systems](https://mlsanity.com/paper/2111.13463/) (2021)
- [Controlling the Risk of Conversational Search via Reinforcement Learning](https://mlsanity.com/paper/2101.06327/) (2021)
- [Unsupervised Question Clarity Prediction Through Retrieved Item Coherency](https://mlsanity.com/paper/2208.04882/) (2022)
- [MIMICS-Duo: Offline & Online Evaluation of Search Clarification](https://mlsanity.com/paper/2206.04417/) (2022)
- [Simulating and Modeling the Risk of Conversational Search](https://mlsanity.com/paper/2201.00235/) (2022)
- [Deciding Whether to Ask Clarifying Questions in Large-Scale Spoken Language Understanding](https://mlsanity.com/paper/2109.12451/) (2021)
- [Estimating the Usefulness of Clarifying Questions and Answers for Conversational Search](https://mlsanity.com/paper/2401.11463/) (2024)

## Built on by (most cited first, 4 of 4)

- [Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization](https://mlsanity.com/paper/2506.06964/) (2025)
- [Conversational Search: From Fundamentals to Frontiers in the LLM Era](https://mlsanity.com/paper/2506.10635/) (2025)
- [RAC: Retrieval-Augmented Clarification for Faithful Conversational Search](https://mlsanity.com/paper/2601.11722/) (2026)
- [CIR at iKAT SCAI 2026: Exploring Clarification Need Prediction in Agentic Conversational Search](https://mlsanity.com/paper/2607.19801/) (2026)

## Abstract (arXiv)

Clarification need prediction (CNP) is a key task in conversational search, aiming to predict whether to ask a clarifying question or give an answer to the current user query. However, current research on CNP suffers from the issues of limited CNP training data and low efficiency. In this paper, we propose a zero-shot and efficient CNP framework (Zef-CNP), in which we first prompt large language models (LLMs) in a zero-shot manner to generate two sets of synthetic queries: ambiguous and specific (unambiguous) queries. We then use the generated queries to train efficient CNP models. Zef-CNP eliminates the need for human-annotated clarification-need labels during training and avoids the use of LLMs with high query latency at query time. To further improve the generation quality of synthetic queries, we devise a topic-, information-need-, and query-aware chain-of-thought (CoT) prompting strategy (TIQ-CoT). Moreover, we enhance TIQ-CoT with counterfactual query generation (CoQu), which guides LLMs first to generate a specific/ambiguous query and then sequentially generate its corresponding ambiguous/specific query. Experimental results show that Zef-CNP achieves superior CNP effectiveness and efficiency compared with zero- and few-shot LLM-based CNP predictors.