mlsanityData to 7 Oct 2026

Sensitivity-Aware Retrieval-Augmented Intent Clarification

arXiv 2603.06025 ↗First posted 6 Mar 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

In conversational search systems, a key component is to determine and clarify the intent behind complex queries. We view intent clarification in light of the exploratory search paradigm, where users, through an iterative, evolving process of selection, exploration and retrieval, transform a visceral or conscious need into a formalized one. Augmenting the clarification component with a retrieval step (retrieval-augmented intent clarification) can seriously enhance clarification performance, especially in domains where Large Language Models (LLMs) lack parametric knowledge. However, in more sensitive domains, such as healthcare, government (e.g. FOIA search) or legal contexts, the retrieval database may contain sensitive information that needs protection. In this paper, we explore the research challenge of developing a retrieval-augmented conversational agent that can act as a mediator and gatekeeper for the sensitive collection. To do that, we also need to know what we are protecting and against what. We propose to tackle this research challenge in three steps: 1) define an attack model, 2) design sensitivity-aware defenses on the retrieval level and 3) develop evaluation methods to measure the trade-off between the level of protection and the system's utility.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 19 of its 43 references that are in the map. First posted on arXiv 6 Mar 2026.

Builds on

19 of 43 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Mask-based Membership Inference Attacks for Retrieval-Augmented Generation26 Oct
  2. 2024Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation27 Jun
  3. 2024Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation30 May

Other references · 16

  1. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  2. 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attackcited by 364
  3. 2024Do Membership Inference Attacks Work on Large Language Models?cited by 188
  4. 2019Asking Clarifying Questions in Open-Domain Information-Seeking Conversationscited by 136
  5. 2020ConvAI3: Generating Clarifying Questions for Open-Domain Dialogue Systems (ClariQ)cited by 55
  6. 2024Don't Say No: Jailbreaking LLM by Suppressing Refusalcited by 53
  7. 2014C-sanitized: a privacy model for document redaction and sanitizationcited by 27
  8. 2024Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignmentcited by 24
  9. 2024A Survey of Conversational Searchcited by 22
  10. 2022QUILL: Query Intent with Large Language Models using Retrieval Augmentation and Multi-stage Distillationcited by 21
  11. 2024Noisy Neighbors: Efficient membership inference attacks against LLMscited by 20
  12. 2025Membership Inference Attacks on Large-Scale Models: A Surveycited by 17
4 more
  1. 2020Query Understanding via Intent Description Generationcited by 8
  2. 2021Conversational Search with Mixed-Initiative -- Asking Good Clarification Questions backed-up by Passage Retrievalcited by 5
  3. 2024Corpus-informed Retrieval Augmented Generation of Clarifying Questionscited by 2
  4. 2024SARA: A Collection of Sensitivity-Aware Relevance Assessmentscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026RAC: Retrieval-Augmented Clarification for Faithful Conversational Search
  2. 2025IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement
  3. 2026When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search
  4. 2025SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents
  5. 2026Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
  6. 2026Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards
  7. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
  8. 2025ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering