Characterizing Rhetorical Misalignment in Decision-Making with Language Models

• URL: http://arxiv.org/abs/2608.14630v1
• Date: Fri, 24 Jul 2026 02:36:00 GMT
• Title: Characterizing Rhetorical Misalignment in Decision-Making with Language Models
• Abstract summary: Large language models (LLMs) are increasingly integrated into high-stakes human-AI decision-making.<n>We study rhetorical misalignment, a failure mode where an LLM uses rhetorically inappropriate forms of presentation for a given decision context.<n>We observe that LLMs induce an average 2.81% rate of harmful decision flips across different models.
• Score: 22.79503625028684
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making? [64.5408523407693]
  Large Language Models (LLMs) are increasingly deployed as autonomous agents in high-stakes domains.<n>We investigate whether induced emotion can influence their sequential decision-making using the Iowa Gambling Task.<n>We find that, different from humans, induced emotion does not significantly bias the decision dynamics of LLM agents on average.
  arXiv  Detail & Related papers  (2026-07-14T11:09:51Z)
• Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making [13.79732306725696]
  Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation.<n>We investigate whether frontier LLMs inherit and propagate this human bias when processing clinical text.
  arXiv  Detail & Related papers  (2026-05-17T02:28:25Z)
• LLMs in Cybersecurity: Friend or Foe in the Human Decision Loop? [0.15293427903448023]
  Large Language Models (LLMs) are transforming human decision-making by acting as cognitive collaborators.<n>This paper investigates how LLMs shape human judgment in security-critical contexts.
  arXiv  Detail & Related papers  (2025-09-08T12:06:06Z)
• Prospect Theory Fails for LLMs: Revealing Instability of Decision-Making under Epistemic Uncertainty [41.94502767947584]
  It remains largely unexplored whether Prospect Theory applies to contemporary Large Language Models.<n>We propose a more general and precise evaluation framework to model LLMs' decision-making behaviour under PT.<n>Our findings suggest that modelling LLMs' decision-making with PT is not consistently reliable.
  arXiv  Detail & Related papers  (2025-08-12T15:02:16Z)
• Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making [71.71796367760112]
  Large language models (LLMs) have shown potential in supporting decision-making applications.<n>We propose a cognitive debiasing approach, self-adaptive cognitive debiasing (SACD)<n>We evaluate SACD on finance, healthcare, and legal decision-making tasks using both open-weight and closed-weight LLMs.
  arXiv  Detail & Related papers  (2025-04-05T11:23:05Z)
• Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments [108.55277188617035]
  Large language models (LLMs) have been widely adopted in various downstream task domains, but their abilities to directly recall and apply factual medical knowledge remains under-explored.<n>We introduce the Medical Knowledge Judgment dataset (MKJ), a dataset derived from the Unified Medical Language System (UMLS), a comprehensive repository of standardized vocabularies and knowledge graphs.<n>Through a binary classification framework, MKJ evaluates LLMs' grasp of fundamental medical facts by having them assess the validity of concise, one-hop statements.
  arXiv  Detail & Related papers  (2025-02-20T05:27:51Z)
• Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context [5.361970694197912]
  This paper proposes a framework, grounded in behavioral economics, to evaluate the decision-making behaviors of large language models (LLMs) We estimate the degree of risk preference, probability weighting, and loss aversion in a context-free setting for three commercial LLMs: ChatGPT-4.0-Turbo, Claude-3-Opus, and Gemini-1.0-pro. Our results reveal that LLMs generally exhibit patterns similar to humans, such as risk aversion and loss aversion, with a tendency to overweight small probabilities.
  arXiv  Detail & Related papers  (2024-06-10T02:14:19Z)
• Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
  Large language models (LLMs) are used to automate decision-making tasks.<n>In this paper, we evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention.<n>We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types.<n>These benchmarks allow us to isolate the ability of LLMs to accurately predict changes resulting from their ability to memorize facts or find other shortcuts.
  arXiv  Detail & Related papers  (2024-04-08T14:15:56Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Leveraging Expert Consistency to Improve Algorithmic Decision Support [62.61153549123407]
  We explore the use of historical expert decisions as a rich source of information that can be combined with observed outcomes to narrow the construct gap. We propose an influence function-based methodology to estimate expert consistency indirectly when each case in the data is assessed by a single expert. Our empirical evaluation, using simulations in a clinical setting and real-world data from the child welfare domain, indicates that the proposed approach successfully narrows the construct gap.
  arXiv  Detail & Related papers  (2021-01-24T05:40:29Z)

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.