Mind the Gap: Aligning Knowledge Bases with User Needs to Enhance Mental Health Retrieval

2025-09-16

AI Summary

Existing mental health knowledge bases suffer from high expansion costs and insufficient semantic coverage, limiting their ability to address users’ informal, context-dependent psychological concerns. Method: We propose a “gap-aware” framework that identifies semantic discrepancies between knowledge bases and real-world user needs—derived from authentic forum data—to guide low-resource, high-impact targeted corpus expansion. Our approach integrates retrieval-augmented generation (RAG) with query rewriting, re-ranking, and hierarchical retrieval to automatically prioritize expansion candidates. Contribution/Results: Experiments show that expanding only 42% of the corpus achieves 95% of the baseline performance—substantially outperforming random expansion, which requires 232%–763% more data. With minimal expansion, our method approaches optimal retrieval performance, establishing a new paradigm for cost-effective, highly adaptive mental health information retrieval.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Metareasoning and Metaheuristics
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Access to reliable mental health information is vital for early help-seeking, yet expanding knowledge bases is resource-intensive and often misaligned with user needs. This results in poor performance of retrieval systems when presented concerns are not covered or expressed in informal or contextualized language. We present an AI-based gap-informed framework for corpus augmentation that authentically identifies underrepresented topics (gaps) by overlaying naturalistic user data such as forum posts in order to prioritize expansions based on coverage and usefulness. In a case study, we compare Directed (gap-informed augmentations) with Non-Directed augmentation (random additions), evaluating the relevance and usefulness of retrieved information across four retrieval-augmented generation (RAG) pipelines. Directed augmentation achieved near-optimal performance with modest expansions--requiring only a 42% increase for Query Transformation, 74% for Reranking and Hierarchical, and 318% for Baseline--to reach ~95% of the performance of an exhaustive reference corpus. In contrast, Non-Directed augmentation required substantially larger and thus practically infeasible expansions to achieve comparable performance (232%, 318%, 403%, and 763%, respectively). These results show that strategically targeted corpus growth can reduce content creation demands while sustaining high retrieval and provision quality, offering a scalable approach for building trusted health information repositories and supporting generative AI applications in high-stakes domains.

Problem

• Aligning mental health knowledge bases with user needs
• Improving retrieval system performance for informal queries
• Reducing resource demands for corpus expansion

Innovation

• AI framework identifies knowledge gaps using user data
• Prioritizes corpus expansions based on coverage and usefulness
• Strategic augmentation reduces content needs while maintaining quality