# Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation

arXiv: https://arxiv.org/abs/2401.16558 · HTML: https://mlsanity.com/paper/2401.16558/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 29 Jan 2024.

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

- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Automated Fact-Checking for Assisting Human Fact-Checkers](https://mlsanity.com/paper/2103.07769/) (2021)
- [Artificial Artificial Artificial Intelligence: Crowd Workers Widely Use Large Language Models for Text Production Tasks](https://mlsanity.com/paper/2306.07899/) (2023)
- [Automated Fact-Checking: A Survey](https://mlsanity.com/paper/2109.11427/) (2021)
- [Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms](https://mlsanity.com/paper/2007.07996/) (2020)
- [Sociodemographic Prompting is Not Yet an Effective Approach for Simulating Subjective Judgments with LLMs](https://mlsanity.com/paper/2311.09730/) (2023)
- [ClaimRank: Detecting Check-Worthy Claims in Arabic and English](https://mlsanity.com/paper/1804.07587/) (2018)
- [Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AI](https://mlsanity.com/paper/2308.07213/) (2023)
- [Misinformation as a harm: structured approaches for fact-checking prioritization](https://mlsanity.com/paper/2312.11678/) (2023)
- [Does AI-Assisted Fact-Checking Disproportionately Benefit Majority Groups Online?](https://mlsanity.com/paper/2302.03782/) (2023)

## Built on by (most cited first, 3 of 3)

- [Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy](https://mlsanity.com/paper/2504.00241/) (2025)
- [Mapping the Potential of Explainable AI for Fairness Along the AI Lifecycle](https://mlsanity.com/paper/2404.18736/) (2024)
- [Auction-Based Regulation for Artificial Intelligence](https://mlsanity.com/paper/2410.01871/) (2024)

## Abstract (arXiv)

The pervasive spread of misinformation and disinformation poses a significant threat to society. Professional fact-checkers play a key role in addressing this threat, but the vast scale of the problem forces them to prioritize their limited resources. This prioritization may consider a range of factors, such as varying risks of harm posed to specific groups of people. In this work, we investigate potential implications of using a large language model (LLM) to facilitate such prioritization. Because fact-checking impacts a wide range of diverse segments of society, it is important that diverse views are represented in the claim prioritization process. This paper examines whether a LLM can reflect the views of various groups when assessing the harms of misinformation, focusing on gender as a primary variable. We pose two central questions: (1) To what extent do prompts with explicit gender references reflect gender differences in opinion in the United States on topics of social relevance? and (2) To what extent do gender-neutral prompts align with gendered viewpoints on those topics? To analyze these questions, we present the TopicMisinfo dataset, containing 160 fact-checked claims from diverse topics, supplemented by nearly 1600 human annotations with subjective perceptions and annotator demographics. Analyzing responses to gender-specific and neutral prompts, we find that GPT 3.5-Turbo reflects empirically observed gender differences in opinion but amplifies the extent of these differences. These findings illuminate AI's complex role in moderating online communication, with implications for fact-checkers, algorithm designers, and the use of crowd-workers as annotators. We also release the TopicMisinfo dataset to support continuing research in the community.