# Characterizing Rhetorical Misalignment in Decision-Making with Language Models

arXiv: https://arxiv.org/abs/2608.14630 · HTML: https://mlsanity.com/paper/2608.14630/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 51 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 14 of 14)

- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [Learning to Complement Humans](https://mlsanity.com/paper/2005.00582/) (2020)
- [CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring](https://mlsanity.com/paper/2505.23575/) (2025)
- [A Decision Theoretic Framework for Measuring AI Reliance](https://mlsanity.com/paper/2401.15356/) (2024)
- [Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians](https://mlsanity.com/paper/2602.19141/) (2026)
- [Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias](https://mlsanity.com/paper/2401.14589/) (2024)
- [CTRL-ALT-DECEIT: Sabotage Evaluations for Automated AI R&D](https://mlsanity.com/paper/2511.09904/) (2025)
- [What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions](https://mlsanity.com/paper/2406.03707/) (2024)
- [Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs](https://mlsanity.com/paper/2507.07186/) (2025)

## Abstract (arXiv)

Human decision-making is often shaped by a range of well-documented cognitive biases. As large language models (LLMs) become increasingly integrated into high-stakes human-AI decision-making, it is important to understand whether their outputs can amplify potential biases, how this influences human decisions, and crucially, whether it can lead to harmful consequences. In this work, we develop a decision-theoretic framework to study rhetorical misalignment, a failure mode where an LLM uses rhetorically inappropriate forms of presentation for a given decision context, thereby inducing suboptimal human decisions. We empirically investigate this phenomenon through a human-subject experiment in realistic clinical decision-making using a dataset curated from the United States Medical Licensing Examination. By measuring how LLM-generated information affects decisions, we observe that LLMs induce an average 2.81% rate of harmful decision flips across different models, where clinician participants change from a correct to an incorrect answer. Rationales reported by participants provide evidence that these revisions are closely related to the language used by LLMs that may induce different types of cognitive biases, including anchoring, authority bias, and loss aversion. To enable scalable evaluation, we instantiate our theoretical framework using decision-makers simulated by LLMs to computationally measure rhetorical misalignment. Our findings reveal a safety concern previously unrecognized in high-stakes domains: a model can be factually aligned yet still induce harm through its rhetorical presentation.