# On Fact and Frequency: LLM Responses to Misinformation Expressed with Uncertainty

arXiv: https://arxiv.org/abs/2503.04271 · HTML: https://mlsanity.com/paper/2503.04271/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 3 of 3)

- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [Factuality Challenges in the Era of Large Language Models](https://mlsanity.com/paper/2310.05189/) (2023)
- [The Perils & Promises of Fact-checking with Large Language Models](https://mlsanity.com/paper/2310.13549/) (2023)

## Built on by (most cited first, 1 of 1)

- [From 'May' to 'Is': Certainty Distortion in Language Model Rewriting](https://mlsanity.com/paper/2606.07951/) (2026)

## Abstract (arXiv)

We study LLM judgments of misinformation expressed with uncertainty. Our experiments study the response of three widely used LLMs (GPT-4o, LlaMA3, DeepSeek-v2) to misinformation propositions that have been verified false and then are transformed into uncertain statements according to an uncertainty typology. Our results show that after transformation, LLMs change their factchecking classification from false to not-false in 25% of the cases. Analysis reveals that the change cannot be explained by predictors to which humans are expected to be sensitive, i.e., modality, linguistic cues, or argumentation strategy. The exception is doxastic transformations, which use linguistic cue phrases such as "It is believed ...".To gain further insight, we prompt the LLM to make another judgment about the transformed misinformation statements that is not related to truth value. Specifically, we study LLM estimates of the frequency with which people make the uncertain statement. We find a small but significant correlation between judgment of fact and estimation of frequency.