Sensitivity-Aware Retrieval-Augmented Intent Clarification
Maik Larooij

TL;DR
This paper proposes a sensitivity-aware retrieval-augmented approach for intent clarification in conversational search, focusing on protecting sensitive data while maintaining system utility.
Contribution
It introduces a framework for developing defenses in retrieval-augmented systems that handle sensitive information, including attack models and evaluation methods.
Findings
Proposed a three-step approach for sensitivity-aware defenses.
Developed evaluation methods for protection-utility trade-offs.
Outlined a new research direction for secure conversational agents.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Advanced Graph Neural Networks · Ethics and Social Impacts of AI
