# Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models

arXiv: https://arxiv.org/abs/2609.23999 · HTML: https://mlsanity.com/paper/2609.23999/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 46 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Finding Neurons in a Haystack: Case Studies with Sparse Probing](https://mlsanity.com/paper/2305.01610/) (2023)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes](https://mlsanity.com/paper/2509.10625/) (2025)
- [Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning](https://mlsanity.com/paper/2607.07316/) (2026)

## Abstract (arXiv)

How large language models (LLMs) integrate patient risk with clinical cost tradeoffs remains poorly understood. We investigated how four open-weight LLMs (Qwen-2.5-7B/32B and Llama-3.1-8B/70B) internally represent cost tradeoffs, how these representations relate to clinical predictions, and whether decisions shift as predicted by the specified cost direction and magnitude. Using a public diabetes dataset, we varied 11 false-negative (FN) to false-positive (FP) cost ratios across three phrasings and examined representations and behavioral outputs. Patient risk was linearly recoverable on par with conventional classifiers (AUC ≈ 0.83), and cost direction was recoverable in every model. However, representational shifts in cost direction tracked output changes only in the two larger models, and responses to cost magnitude were predominantly direction-agnostic. Only 2 of 12 model-phrasings showed both opposing responses to increasing FN versus FP costs and cost-correct ordering. Representationally, a direction fitted on one cost side did not invert when transferred to the other, as expected under mirror-symmetric encoding. These findings suggest that LLMs encode risk and cost information but do not reliably integrate them into cost-correct decisions. Clinical evaluations should therefore include tradeoff tests, phrasing sensitivity, and default operating points alongside predictive performance.