OwlerLite: Scope- and Freshness-Aware Web Retrieval for LLM Assistants

2026-01-25

AI Summary

This work addresses a critical limitation in current browser-based large language model (LLM) assistants employing retrieval-augmented generation (RAG): their reliance on static, outdated indices that offer users no control over the scope of information sources or data freshness, often leading to untrustworthy or stale responses. To overcome this, the paper introduces a novel client-side RAG system that uniquely integrates user-defined, reusable source scopes with a dynamic freshness-aware mechanism. By leveraging semantic change detection to monitor web page updates in real time and trigger selective re-indexing, the system unifies textual relevance, user-specified source constraints, and content recency into a cohesive retrieval model. This approach significantly enhances the timeliness, relevance, and trustworthiness of retrieved results while ensuring transparent and user-controllable provenance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Browser-based language models often use retrieval-augmented generation (RAG) but typically rely on fixed, outdated indices that give users no control over which sources are consulted. This can lead to answers that mix trusted and untrusted content or draw on stale information. We present OwlerLite, a browser-based RAG system that makes user-defined scopes and data freshness central to retrieval. Users define reusable scopes-sets of web pages or sources-and select them when querying. A freshness-aware crawler monitors live pages, uses a semantic change detector to identify meaningful updates, and selectively re-indexes changed content. OwlerLite integrates text relevance, scope choice, and recency into a unified retrieval model. Implemented as a browser extension, it represents a step toward more controllable and trustworthy web assistants.

Problem

• retrieval-augmented generation
• web retrieval
• data freshness
• source control
• trustworthy assistants

Innovation

• scope-aware retrieval
• freshness-aware crawling
• semantic change detection
• retrieval-augmented generation
• controllable web assistant