SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling
Eliya Naomi Aharon, Meytal Grimland, Avi Segal, Loona Ben Dayan, Inbar Shenfeld + 2 more
TLDR
SAGE is a graph-enhanced framework that integrates clinical knowledge with LLMs for strategy-aware, theory-driven online mental health counseling.
Key contributions
- SAGE integrates clinical knowledge with LLMs using a graph for strategy-aware online counseling.
- Constructs a heterogeneous graph unifying conversational dynamics and psychological theory.
- Employs a Next Strategy Classifier to identify optimal therapeutic interventions.
- Uses Graph-Aware Attention to condition LLMs for clinically deep and relevant responses.
Why it matters
General-purpose LLMs often lack the critical clinical reasoning needed for safe and effective mental health counseling. SAGE addresses this by integrating structured psychological frameworks with generative AI, enhancing therapeutic depth. This framework serves as a vital decision-support tool, augmenting human expertise in high-stakes crisis counseling.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.