analiza aiqbench
This research proposes "future querying" as a method to leverage large language models as implicit medical world models, allowing them to answer time-indexed clinical queries directly from unstructured text without task-specific retraining. The study demonstrates that small, locally fine-tuned open-weight models can effectively capture clinical dynamics comparable to larger proprietary systems, offering a viable path for privacy-preserving, on-premise deployment in healthcare settings.
Future Querying: Can LLMs Serve as Implicit Medical World Models?
arXiv:2608.23248v1 Announce Type: cross Abstract: Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured text. To address this, we introduce future querying, a paradigm that probes whether large language models (LLMs) can function as implicit medical world models by evaluating their ability to answer time-indexed clinical queries about a patient's future. Our framework operates on unstructured clinical documentation using endpoint-agnostic training, enabling a single model to answer diverse clinical queries over patient trajectories without manual feature engineering or task-specific retraining. We show that small, locally fine-tuned open-weight models can match or approach larger proprietary systems, making the framework suitable for privacy-preserving, on-premise deployment. Evaluated on a new synthetic medical reports dataset and real ICU notes from the MIMIC-IV dataset, our results provide encouraging evidence that LLMs can capture aspects of clinical dynamics.
Title:Future Querying: Can LLMs Serve as Implicit Medical World Models?
Abstract:Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured text. To address this, we introduce future querying, a paradigm that probes whether large language models (LLMs) can function as implicit medical world models by evaluating their ability to answer time-indexed clinical queries about a patient's future. Our framework operates on unstructured clinical documentation using endpoint-agnostic training, enabling a single model to answer diverse clinical queries over patient trajectories without manual feature engineering or task-specific retraining. We show that small, locally fine-tuned open-weight models can match or approach larger proprietary systems, making the framework suitable for privacy-preserving, on-premise deployment. Evaluated on a new synthetic medical reports dataset and real ICU notes from the MIMIC-IV dataset, our results provide encouraging evidence that LLMs can capture aspects of clinical dynamics.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2608.23248 [cs.CL]
(or arXiv:2608.23248v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.23248 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 244 cuvinte
Subiecte conexe
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
Links #5: 2026/07
LessWrong · 31 iul. 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
Presentation: Architecting the Data Layer for AI Agents: from Transactional Systems to MCP and Semantic Models
InfoQ · 29 aug. 2026