# Aligning Probabilistic Beliefs under Informative Missingness: LLM Steerability in Clinical Reasoning

arXiv: https://arxiv.org/abs/2512.00479 · HTML: https://mlsanity.com/paper/2512.00479/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 32 of its 73 references that are in the map.
- First posted on arXiv 29 Nov 2025.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [Enabling Language Models to Fill in the Blanks](https://mlsanity.com/paper/2005.05339/) (2020)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling](https://mlsanity.com/paper/2311.08718/) (2023)
- [Confidence Improves Self-Consistency in LLMs](https://mlsanity.com/paper/2502.06233/) (2025)
- [SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales](https://mlsanity.com/paper/2405.20974/) (2024)
- [LUQ: Long-text Uncertainty Quantification for LLMs](https://mlsanity.com/paper/2403.20279/) (2024)
- [Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective](https://mlsanity.com/paper/2406.00793/) (2024)
- [Uncertainty Quantification for In-Context Learning of Large Language Models](https://mlsanity.com/paper/2402.10189/) (2024)
- [Large Language Models are Powerful Electronic Health Record Encoders](https://mlsanity.com/paper/2502.17403/) (2025)
- [LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation](https://mlsanity.com/paper/2410.21520/) (2024)
- [Uncertainty Estimation in Autoregressive Structured Prediction](https://mlsanity.com/paper/2002.07650/) (2020)
- [Prompting Large Language Models for Zero-Shot Clinical Prediction with Structured Longitudinal Electronic Health Record Data](https://mlsanity.com/paper/2402.01713/) (2024)
- [In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning](https://mlsanity.com/paper/2510.10981/) (2025)
- [Bayesian scaling laws for in-context learning](https://mlsanity.com/paper/2410.16531/) (2024)
- [LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.14043/) (2024)
- [Data Imputation using Large Language Model to Accelerate Recommendation System](https://mlsanity.com/paper/2407.10078/) (2024)
- [Multimodal Medical Code Tokenizer](https://mlsanity.com/paper/2502.04397/) (2025)
- [Understanding prompt engineering may not require rethinking generalization](https://mlsanity.com/paper/2310.03957/) (2023)
- [AbsenceBench: Language Models Can't Tell What's Missing](https://mlsanity.com/paper/2506.11440/) (2025)
- [Exchangeable Sequence Models Quantify Uncertainty Over Latent Concepts](https://mlsanity.com/paper/2408.03307/) (2024)
- [MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis](https://mlsanity.com/paper/2506.03750/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly deployed for clinical reasoning tasks, which inherently require eliciting calibrated probabilistic beliefs based on available evidence. However, real-world clinical data are frequently incomplete, with missingness patterns often informative of patient prognosis; for example, ordering a rare laboratory test reflects a clinician's latent suspicion. In this work, we investigate whether LLMs can be steered to leverage this informative missingness for prognostic inference. To evaluate how well LLMs align their verbalized probabilistic beliefs with an underlying target distribution, we analyze three common prompt-based interventions: explicit serialization, instruction steering, and in-context learning. We introduce a bias-variance decomposition of the log-loss to clarify the mechanisms driving gains in predictive performance. Using a real-world intensive care testbed, we find that while explicit structural steering and in-context learning can improve probabilistic alignment, the models do not natively leverage informative missingness without careful interventions.