Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2026

Abstract

As Large Language Models (LLMs) increasingly serve as interfaces for proprietary data (e.g., enterprise knowledge bases, legal statutes), ensuring their fidelity to trusted internal information is paramount. While integrating real-time web search can enhance model utility, it introduces a critical vulnerability: the ingestion of conflicting, misleading, or hallucinated content from the open web can override the model's adherence to its verified internal knowledge. We define this failure mode as search-induced distortion, a significant risk in high-stakes domains where the internal knowledge base serves as the absolute ground truth.To address this challenge, we present PurifAI, a proactive, model-agnostic, cache-level purification system designed for safety- and compliance-sensitive deployments. Rather than serving as a general fact-checking engine, PurifAI is explicitly designed to preserve knowledge alignment with a pre-defined trusted knowledge core. It automatically generates diagnostic probes from trusted documents to identify and neutralize searched web content that conflicts with the canonical internal source before such content distorts the LLM's responses. Extensive evaluations on news, encyclopedic, and legal domains show that PurifAI effectively improves alignment with the trusted core, identifying and blocking distortive content at the source and achieving repair success rates above 70% across mainstream LLMs. Our work offers a practical safeguard for enterprises and other high-stakes applications seeking to integrate web-augmented LLMs without compromising policy consistency and trusted knowledge integrity.

Keywords

Web-Augmented LLMs, Web data cleaning, Knowledge Alignment

Discipline

Artificial Intelligence and Robotics | Information Security

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

SIGIR '26: Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, Melbourne, Australia, July 20-24

First Page

1914

Last Page

1924

ISBN

9798400725999

Identifier

10.1145/3805712.3809751

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3805712.3809751

Download

Share

COinS