# MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support

arXiv: https://arxiv.org/abs/2604.20022 · HTML: https://mlsanity.com/paper/2604.20022/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 11 of its 53 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 11 of 11)

- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://mlsanity.com/paper/2311.16079/) (2023)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator](https://mlsanity.com/paper/2403.08495/) (2024)
- [Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.19630/) (2025)
- [ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning](https://mlsanity.com/paper/2512.07795/) (2025)
- [MedKGI: Iterative Differential Diagnosis with Medical Knowledge Graphs and Information-Guided Inquiring](https://mlsanity.com/paper/2512.24181/) (2025)
- [MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions](https://mlsanity.com/paper/2602.17308/) (2026)
- [Conversational Disease Diagnosis via External Planner-Controlled Large Language Models](https://mlsanity.com/paper/2404.04292/) (2024)

## Built on by (most cited first, 1 of 1)

- [CLIMB: A Clinical Multimorbidity Benchmark for Diagnosing Co-occurring Conditions through Multiturn Conversations](https://mlsanity.com/paper/2609.35462/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used for conversational clinical decision support, yet they conflate next token prediction with probabilistic decision making. We argue that this conflation reflects an architectural limitation: such systems lack explicit posterior tracking, controllable abstention thresholds, and auditable reasoning chains. We introduce MoBayes, a Modular Bayesian dialogue framework that separates reasoning from language. The LLM acts only as a language interface, parsing patient conversation into structured observations, while a Bayesian module performs probabilistic inference over these observations to update posteriors, select follow-up questions via expected-information-gain and determine when to stop or defer through calibrated decision thresholds. This design enables explicit posterior tracking, controllable selective decision-making, and replaceable population-specific statistical backends without retraining the language model. Across empirical and LLM-generated knowledge bases, MoBayes outperforms standalone frontier LLM doctors, including matched model-family comparisons where inexpensive sensor models paired with MoBayes exceed larger autonomous models at lower cost. The advantage persists under adversarial patient communication styles and across varying diagnostic scenarios. These results suggest that reliable conversational clinical decision support systems should separate probabilistic reasoning from language generation rather than scaling model size alone. Code is available at https://anonymous.4open.science/r/MoBayes/