Statistics, Not Scale: Modular Medical Dialogue with Bayesian Belief Engine

• URL: http://arxiv.org/abs/2604.20022v1
• Date: Tue, 21 Apr 2026 21:59:57 GMT
• Title: Statistics, Not Scale: Modular Medical Dialogue with Bayesian Belief Engine
• Abstract summary: Large language models are increasingly deployed as autonomous diagnostic agents, yet they conflate two fundamentally different capabilities.<n>We introduce BMBE, a modular diagnostic dialogue framework that enforces a strict separation between language and reasoning.
• Score: 51.722324399751294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models are increasingly deployed as autonomous diagnostic agents, yet they conflate two fundamentally different capabilities: natural-language communication and probabilistic reasoning. We argue that this conflation is an architectural flaw, not an engineering shortcoming. We introduce BMBE (Bayesian Medical Belief Engine), a modular diagnostic dialogue framework that enforces a strict separation between language and reasoning: an LLM serves only as a sensor, parsing patient utterances into structured evidence and verbalising questions, while all diagnostic inference resides in a deterministic, auditable Bayesian engine. Because patient data never enters the LLM, the architecture is private by construction; because the statistical backend is a standalone module, it can be replaced per target population without retraining. This separation yields three properties no autonomous LLM can offer: calibrated selective diagnosis with a continuously adjustable accuracy-coverage tradeoff, a statistical separation gap where even a cheap sensor paired with the engine outperforms a frontier standalone model from the same family at a fraction of the cost, and robustness to adversarial patient communication styles that cause standalone doctors to collapse. We validate across empirical and LLM-generated knowledge bases against frontier LLMs, confirming the advantage is architectural, not informational.

Related papers

• Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report Generation [66.62662330558906]
  CORAL is a multimodal framework that integrates spatial grounding and concept-level supervision into a unified reasoning process.<n>CORAL employs a prompt-driven medical segmentation model to localize lesions and predicts multi-class clinical attributes through a Concept Bottleneck module.<n>Experiments on BUS-CoT and IU X-ray datasets demonstrate consistent improvements in diagnostic accuracy, concept consistency, and report quality over strong general-purpose and medical MLLMs.
  arXiv  Detail & Related papers  (2026-09-14T10:21:23Z)
• Language Models as Interfaces, Not Oracles: A Hybrid LLM-ML System for Pediatric Appendicitis [1.0312968200748116]
  ClaMPAPP (Clinical Language-assisted Machine-learning Pipeline for Appendicitis) is a hybrid system that uses an LLM as an interface rather than as the final decision-maker.<n>We evaluated ClaMPAPP on two independent pediatric appendicitis cohorts from German hospitals.
  arXiv  Detail & Related papers  (2026-06-17T15:22:51Z)
• SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems [0.9786690381850356]
  We present SymptomWise, a framework that separates language understanding from diagnostic reasoning.<n>The system combines expert-curated medical knowledge, deterministic codex-driven inference, and constrained use of large language models.<n>This architecture improves traceability, reduces unsupported conclusions, and enables modular evaluation of system components.
  arXiv  Detail & Related papers  (2026-04-07T19:00:53Z)
• IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery [61.15184885636171]
  In the presence of confounding between an endogenous variable and the outcome, instrumental variables (IVs) are used to isolate the causal effect of the endogenous variable.<n>We investigate whether large language models (LLMs) can aid in this task.<n>We introduce IV Co-Scientist, a multi-agent system that proposes, critiques, and refines IVs for a given treatment-outcome pair.
  arXiv  Detail & Related papers  (2026-02-08T12:28:29Z)
• Evaluating an evidence-guided reinforcement learning framework in aligning light-parameter large language models with decision-making cognition in psychiatric clinical reasoning [29.976546632432512]
  Large language models (LLMs) hold transformative potential for medical decision support yet their application in psychiatry remains constrained by hallucinations and superficial reasoning.<n>Here we introduce ClinMPO, a reinforcement learning framework designed to align the internal reasoning of LLMs with professional psychiatric practice.
  arXiv  Detail & Related papers  (2026-02-06T07:21:08Z)
• A Federated and Parameter-Efficient Framework for Large Language Model Training in Medicine [59.78991974851707]
  Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis.<n>Most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems.<n>We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications.
  arXiv  Detail & Related papers  (2026-01-29T18:48:21Z)
• Task-Awareness Improves LLM Generations and Uncertainty [48.857040212979484]
  Bayes-optimal responses consistently outperform standard decoding methods like beam search.<n>Our decision-theoretic framework is applicable to any problem that admits a latent response structure.
  arXiv  Detail & Related papers  (2026-01-29T10:16:23Z)
• Standardization of Psychiatric Diagnoses -- Role of Fine-tuned LLM Consortium and OpenAI-gpt-oss Reasoning LLM Enabled Decision Support System [3.629588822458722]
  We propose a Fine-Tuned Large Language Model (LLM) Consortium and OpenAI-gpt-oss Reasoning LLM-enabled Decision Support System.<n>The diagnostic predictions from individual models are aggregated through a consensus-based decision-making process.<n>A prototype of the proposed platform was developed in collaboration with the U.S. Army Medical Research Team in Norfolk, Virginia, USA.
  arXiv  Detail & Related papers  (2025-10-29T14:54:22Z)
• CANDLE: A Cross-Modal Agentic Knowledge Distillation Framework for Interpretable Sarcopenia Diagnosis [3.0245458192729466]
  CANDLE mitigates the interpretability-performance trade-off, enhances predictive accuracy, and preserves high decision consistency.<n>The framework offers a scalable approach to knowledge assetization of TML models, enabling interpretable, reproducible, and clinically aligned decision support in sarcopenia and potentially broader medical domains.
  arXiv  Detail & Related papers  (2025-07-26T15:50:08Z)
• DocCHA: Towards LLM-Augmented Interactive Online diagnosis System [17.975659876934895]
  DocCHA is a confidence-aware, modular framework that emulates clinical reasoning by decomposing the diagnostic process into three stages.<n> evaluated on two real-world Chinese consultation datasets.
  arXiv  Detail & Related papers  (2025-07-10T15:52:04Z)
• STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond [68.47402386668846]
  We introduce Structured Reasoning In Critical Text Assessment (STRICTA) to model text assessment as an explicit, step-wise reasoning process.<n>STRICTA breaks down the assessment into a graph of interconnected reasoning steps drawing on causality theory.<n>We apply STRICTA to a dataset of over 4000 reasoning steps from roughly 40 biomedical experts on more than 20 papers.
  arXiv  Detail & Related papers  (2024-09-09T06:55:37Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.