SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling

TL;DR

SAGE is a novel framework that enhances AI-driven online counseling by integrating clinical knowledge with conversational data through graph structures and strategic prompts.

Contribution

It introduces a strategy-aware, graph-enhanced architecture that improves therapeutic intervention prediction and response quality in AI counseling systems.

Findings

Outperforms baselines in strategy prediction accuracy.

Generates responses with greater clinical depth.

Provides actionable intervention recommendations.

Abstract

Effective mental health counseling is a complex, theory-driven process requiring the simultaneous integration of psychological frameworks, real-time distress signals, and strategic intervention planning. This level of clinical reasoning is critical for safety and therapeutic effectiveness but is often missing in general-purpose Large Language Models (LLMs). We introduce SAGE (Strategy-Aware Graph-Enhanced), a novel framework designed to bridge the gap between structured clinical knowledge and generative AI. SAGE constructs a heterogeneous graph that unifies conversational dynamics with a psychologically grounded layer, explicitly anchoring interactions in a theory-driven lexicon. Our architecture first employs a Next Strategy Classifier to identify the optimal therapeutic intervention. Subsequently, a Graph-Aware Attention mechanism projects graph-derived structural signals into soft prompts, conditioning the LLM to generate responses that maintain clinical depth. Validated through both automated metrics and expert human evaluation, SAGE outperforms baselines in strategy prediction and recommended response quality. By providing actionable intervention recommendations, SAGE serves as a cutting-edge decision-support tool designed to augment human expertise in high-stakes crisis counseling.