SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling
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.
Cite
@article{arxiv.2604.26630,
title = {SAGE: A Strategy-Aware Graph-Enhanced Generation Framework For Online Counseling},
author = {Eliya Naomi Aharon and Meytal Grimland and Avi Segal and Loona Ben Dayan and Inbar Shenfeld and Yossi Levi Belz and Kobi Gal},
journal= {arXiv preprint arXiv:2604.26630},
year = {2026}
}
Comments
Full version of the work accepted as a short paper at the 34th ACM Conference on User Modeling, Adaptation and Personalization (UMAP '26). 9 pages, 4 figures, 5 tables