Enhancing Adaptive Behavioral Interventions with LLM Inference from Participant Described States

Karine Karine, Benjamin M. Marlin
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

The use of reinforcement learning (RL) methods to support health behavior change via personalized and just-in-time adaptive interventions is of significant interest to health and behavioral science researchers focused on problems such as smoking cessation support and physical activity promotion. However, RL methods are often applied to these domains using a small collection of context variables to mitigate the significant data scarcity issues that arise from practical limitations on the design of adaptive intervention trials. In this paper, we explore an approach to significantly expanding the state space of an adaptive intervention without impacting data efficiency. The proposed approach enables intervention participants to provide natural language descriptions of aspects of their current state. It then leverages inference with pre-trained large language models (LLMs) to better align the policy of a base RL method with these state descriptions. To evaluate our method, we develop a novel physical activity intervention simulation environment that generates text-based state descriptions conditioned on latent state variables using an auxiliary LLM. We show that this approach has the potential to significantly improve the performance of online policy learning methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-karine25a, title = {Enhancing Adaptive Behavioral Interventions with {LLM} Inference from Participant Described States}, author = {Karine, Karine and Marlin, Benjamin M.}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/karine25a/karine25a.pdf}, url = {https://proceedings.mlr.press/v298/karine25a.html}, abstract = {The use of reinforcement learning (RL) methods to support health behavior change via personalized and just-in-time adaptive interventions is of significant interest to health and behavioral science researchers focused on problems such as smoking cessation support and physical activity promotion. However, RL methods are often applied to these domains using a small collection of context variables to mitigate the significant data scarcity issues that arise from practical limitations on the design of adaptive intervention trials. In this paper, we explore an approach to significantly expanding the state space of an adaptive intervention without impacting data efficiency. The proposed approach enables intervention participants to provide natural language descriptions of aspects of their current state. It then leverages inference with pre-trained large language models (LLMs) to better align the policy of a base RL method with these state descriptions. To evaluate our method, we develop a novel physical activity intervention simulation environment that generates text-based state descriptions conditioned on latent state variables using an auxiliary LLM. We show that this approach has the potential to significantly improve the performance of online policy learning methods.} }
Endnote
%0 Conference Paper %T Enhancing Adaptive Behavioral Interventions with LLM Inference from Participant Described States %A Karine Karine %A Benjamin M. Marlin %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-karine25a %I PMLR %U https://proceedings.mlr.press/v298/karine25a.html %V 298 %X The use of reinforcement learning (RL) methods to support health behavior change via personalized and just-in-time adaptive interventions is of significant interest to health and behavioral science researchers focused on problems such as smoking cessation support and physical activity promotion. However, RL methods are often applied to these domains using a small collection of context variables to mitigate the significant data scarcity issues that arise from practical limitations on the design of adaptive intervention trials. In this paper, we explore an approach to significantly expanding the state space of an adaptive intervention without impacting data efficiency. The proposed approach enables intervention participants to provide natural language descriptions of aspects of their current state. It then leverages inference with pre-trained large language models (LLMs) to better align the policy of a base RL method with these state descriptions. To evaluate our method, we develop a novel physical activity intervention simulation environment that generates text-based state descriptions conditioned on latent state variables using an auxiliary LLM. We show that this approach has the potential to significantly improve the performance of online policy learning methods.
APA
Karine, K. & Marlin, B.M.. (2025). Enhancing Adaptive Behavioral Interventions with LLM Inference from Participant Described States. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/karine25a.html.

Related Material