mlsanityData to 14 Oct 2026

CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval

arXiv 2405.15784 ↗First posted 28 Apr 2024cs.IR cs.AI cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Users often make ambiguous requests that require clarification. We study the problem of asking clarification questions in an information retrieval setting, where systems often face ambiguous search queries and it is challenging to turn the uncertainty in the retrieval model into a natural language question. We present CLARINET, a system that asks informative clarification questions by choosing questions whose answers would maximize certainty in the correct candidate. Our approach works by augmenting a large language model (LLM) to condition on a retrieval distribution, finetuning end-to-end to generate the question that would have maximized the rank of the true candidate at each turn. When evaluated on a real-world retrieval dataset of users searching for books, our system outperforms traditional heuristics such as information gain on retrieval success by 17% and vanilla-prompted LLMs by 39% relative.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 9 of its 22 references that are in the map. First posted on arXiv 28 Apr 2024.

Builds on

9 of 22 references.

References · 9

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  2. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  3. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  4. 2018Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Informationcited by 115
  5. 2019Answer-based Adversarial Training for Generating Clarification Questionscited by 43
  6. 2023Decomposing Complex Queries for Tip-of-the-tongue Retrievalcited by 24
  7. 2021Open-domain clarification question generation without question examplescited by 20
  8. 2019Interactive Classification by Asking Informative Questionscited by 16
  9. 2017Question Asking as Program Generationcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 11.

20 papers.

Sort:

By area:

  1. 2025CollabLLM: From Passive Responders to Active Collaboratorscited by 124
  2. 2025BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Designcited by 24
  3. 2025Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMscited by 20
  4. 2024Contextualized Evaluations: Judging Language Model Responses to Underspecified Queriescited by 12
  5. 2025Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimizationcited by 10
  6. 2025InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Contextcited by 8
  7. 2025Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questionscited by 8
  8. 2026Uncertainty-Aware Clarification in LLM Agents with Information Gaincited by 8
  9. 2025Browsing Lost Unformed Recollections: A Benchmark for Tip-of-the-Tongue Search and Reasoningcited by 7
  10. 2026Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirerscited by 3
  11. 2025GTAlign: Game-Theoretic Alignment of LLM Assistants for Social Welfarecited by 2
  12. 2026Question Difficulty Estimation for Large Language Models via Answer Plausibility Scoringcited by 2
8 more
  1. 2026Multi-Turn Agentic Scientific Literature Search via Workflow Inductioncited by 2
  2. 2026Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMscited by 2
  3. 2026Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critiquecited by 2
  4. 2026Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversationcited by 0
  5. 2026BALAR : A Bayesian Agentic Loop for Active Reasoningcited by 0
  6. 2026CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurementcited by 0
  7. 2026Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agentscited by 0
  8. 2026Rational Clarification by Assistive Agents via Value-of-Information Reasoningcited by 0