TY - GEN
T1 - SAGE
T2 - 34th ACM International Conference on User Modeling, Adaptation and Personalization, UMAP 2026
AU - Aharon, Eliya Naomi
AU - Grimland, Meytal
AU - Segal, Avi
AU - Ben Dayan, Loona
AU - Shenfeld, Inbar
AU - Levi Belz, Yossi
AU - Gal, Kobi
N1 - Publisher Copyright:
© 2026 Copyright held by the owner/author(s).
PY - 2026/6/7
Y1 - 2026/6/7
N2 - Effective online 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 Generation Framework), 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 online crisis counseling.
AB - Effective online 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 Generation Framework), 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 online crisis counseling.
KW - Graph Neural Networks
KW - Large Language Models
KW - Online Mental Health Support
UR - https://www.scopus.com/pages/publications/105042801018
U2 - 10.1145/3774935.3806785
DO - 10.1145/3774935.3806785
M3 - Conference contribution
AN - SCOPUS:105042801018
T3 - UMAP 2026 - Proceedings of the 34th ACM International Conference on User Modeling, Adaptation and Personalization
SP - 435
EP - 439
BT - UMAP 2026 - Proceedings of the 34th ACM International Conference on User Modeling, Adaptation and Personalization
PB - Association for Computing Machinery, Inc
Y2 - 8 June 2026 through 11 June 2026
ER -