# LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models

arXiv: https://arxiv.org/abs/2512.23025 · HTML: https://mlsanity.com/paper/2512.23025/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 51 references that are in the map.
- First posted on arXiv 28 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [A Picture is Worth A Thousand Numbers: Enabling LLMs Reason about Time Series via Visualization](https://mlsanity.com/paper/2411.06018/) (2024)
- [Voila-A: Aligning Vision-Language Models with User's Gaze Attention](https://mlsanity.com/paper/2401.09454/) (2023)
- [By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting](https://mlsanity.com/paper/2407.10385/) (2024)
- [HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis](https://mlsanity.com/paper/2506.19291/) (2025)
- [DepressLLM: Interpretable domain-adapted language model for depression detection from real-world narratives](https://mlsanity.com/paper/2508.08591/) (2025)
- [Social Isolation and Serious Mental Illness: The Role of Context-Aware Mobile Interventions](https://mlsanity.com/paper/2311.10302/) (2023)
- [Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout](https://mlsanity.com/paper/2507.10430/) (2025)

## Built on by (most cited first, 3 of 3)

- [Learning Transferable Sensor Models via Language-Informed Pretraining](https://mlsanity.com/paper/2603.11950/) (2026)
- [PULSE: Agentic Investigation with Passive Sensing for Proactive Affective Intervention in Cancer Survivorship](https://mlsanity.com/paper/2605.17679/) (2026)
- [TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models](https://mlsanity.com/paper/2609.13457/) (2026)

## Abstract (arXiv)

Multimodal health sensing offers rich behavioral signals for assessing mental health, yet translating these numerical time-series measurements into natural language remains challenging. Current LLMs cannot natively ingest long-duration sensor streams, and paired sensor-text datasets are scarce. To address these challenges, we introduce LENS, a framework that aligns multimodal sensing data with language models to generate clinically grounded mental-health narratives. LENS first constructs a large-scale dataset by transforming Ecological Momentary Assessment (EMA) responses related to depression and anxiety symptoms into natural-language descriptions, yielding over 100,000 sensor-text QA pairs from 258 participants. To enable native time-series integration, we train a patch-level encoder that projects raw sensor signals directly into an LLM's representation space. Our results show that LENS outperforms strong baselines on standard NLP metrics and task-specific measures of symptom-severity accuracy. A user study with 13 mental-health professionals further indicates that LENS-produced narratives are comprehensive and clinically meaningful. Ultimately, our approach advances LLMs as interfaces for health sensing, providing a scalable path toward models that can reason over raw behavioral signals and support downstream clinical decision-making.