# Uncertainty-Aware Calibrated Clinical Text Classification with Large Language Models

arXiv: https://arxiv.org/abs/2509.19375 · HTML: https://mlsanity.com/paper/2509.19375/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [AlpaCare:Instruction-tuned Large Language Models for Medical Application](https://mlsanity.com/paper/2310.14558/) (2023)
- [Med42-v2: A Suite of Clinical LLMs](https://mlsanity.com/paper/2408.06142/) (2024)
- [Prompt Consistency for Zero-Shot Task Generalization](https://mlsanity.com/paper/2205.00049/) (2022)
- [SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models](https://mlsanity.com/paper/2403.02509/) (2024)
- [Calibrating the Confidence of Large Language Models by Eliciting Fidelity](https://mlsanity.com/paper/2404.02655/) (2024)
- [On Second-Order Scoring Rules for Epistemic Uncertainty Quantification](https://mlsanity.com/paper/2301.12736/) (2023)
- [Simulation-Based Inference: A Practical Guide](https://mlsanity.com/paper/2508.12939/) (2025)
- [Reliable Gradient-free and Likelihood-free Prompt Tuning](https://mlsanity.com/paper/2305.00593/) (2023)
- [Uncertainty-aware abstention in medical diagnosis based on medical texts](https://mlsanity.com/paper/2502.18050/) (2025)
- [The Consistency Hypothesis in Uncertainty Quantification for Large Language Models](https://mlsanity.com/paper/2506.21849/) (2025)
- [SimBa: An Efficient Tool for Approximating Rips-filtration Persistence via Simplicial Batch-collapse](https://mlsanity.com/paper/1609.07517/) (2016)

## Abstract (arXiv)

Large language models are increasingly used for clinical text classification, where overconfident misclassifications can directly affect patient care. Existing black-box uncertainty methods attach a confidence score to a fixed LLM prediction using softmax probabilities, verbalised confidence, prompt agreement, or generation consistency. These signals are often poorly calibrated and offer no mechanism for combining model evidence with prior clinical belief. We instead formulate closed-set clinical classification as likelihood-free posterior inference over diagnostic hypotheses. A prompt-conditioned LLM is treated as a class-conditional stochastic simulator: for each candidate diagnosis it generates synthetic clinical descriptions, which are compared with the observed case in an embedding summary space. Sequential Monte Carlo Approximate Bayesian Computation then yields a posterior over diagnoses from which both the prediction and its uncertainty are derived. We instantiate three variants spanning a cost-fidelity spectrum: multinomial SMC (M-SMC), Dirichlet SMC (D-SMC), and an amortised Dirichlet posterior network (ABI) for deployment-time inference. Across three clinical benchmarks and six open LLMs, the inferred posterior separates correct predictions from errors more sharply than black-box confidence, with misclassification-detection AUROC on MultiCare of 0.923 for M-SMC against 0.760 for softmax and 0.584 for a consistency baseline. The posterior also accepts an explicit clinician prior, recovering the correct diagnosis from a deliberately misleading one, and remains diffuse on out-of-distribution presentations. We release OLB-300, an expert-validated clinical uncertainty-quantification benchmark of oral-lesion vignettes.