LENS creates over 100,000 sensor-text QA pairs from 258 participants' EMA data and trains a patch-level encoder that projects raw multimodal sensor streams into an LLM's space, enabling generation of clinically grounded depression and anxiety narratives that outperform baselines on NLP and symptom-1
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models
LENS creates over 100,000 sensor-text QA pairs from 258 participants' EMA data and trains a patch-level encoder that projects raw multimodal sensor streams into an LLM's space, enabling generation of clinically grounded depression and anxiety narratives that outperform baselines on NLP and symptom-1