# Are Stereotypes Leading LLMs' Zero-Shot Stance Detection ?

arXiv: https://arxiv.org/abs/2510.20154 · HTML: https://mlsanity.com/paper/2510.20154/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems](https://mlsanity.com/paper/1805.04508/) (2018)
- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [Demographic Dialectal Variation in Social Media: A Case Study of African-American English](https://mlsanity.com/paper/1608.08868/) (2016)
- [SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning](https://mlsanity.com/paper/2307.10234/) (2023)
- [Prompting and Fine-Tuning Open-Sourced Large Language Models for Stance Classification](https://mlsanity.com/paper/2309.13734/) (2023)
- [DEEM: Dynamic Experienced Expert Modeling for Stance Detection](https://mlsanity.com/paper/2402.15264/) (2024)
- [Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning](https://mlsanity.com/paper/2212.10392/) (2022)
- [Fair Text Classification with Wasserstein Independence](https://mlsanity.com/paper/2311.12689/) (2023)
- [Relative Counterfactual Contrastive Learning for Mitigating Pretrained Stance Bias in Stance Detection](https://mlsanity.com/paper/2405.10991/) (2024)

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

- [SICI: A Semantic-Pragmatic Complexity Index Reveals Regime Shifts in LLM Stance Detection](https://mlsanity.com/paper/2606.13189/) (2026)

## Abstract (arXiv)

Large Language Models inherit stereotypes from their pretraining data, leading to biased behavior toward certain social groups in many Natural Language Processing tasks, such as hateful speech detection or sentiment analysis. Surprisingly, the evaluation of this kind of bias in stance detection methods has been largely overlooked by the community. Stance Detection involves labeling a statement as being against, in favor, or neutral towards a specific target and is among the most sensitive NLP tasks, as it often relates to political leanings. In this paper, we focus on the bias of Large Language Models when performing stance detection in a zero-shot setting. We automatically annotate posts in pre-existing stance detection datasets with two attributes: dialect or vernacular of a specific group and text complexity/readability, to investigate whether these attributes influence the model's stance detection decisions. Our results show that LLMs exhibit significant stereotypes in stance detection tasks, such as incorrectly associating pro-marijuana views with low text complexity and African American dialect with opposition to Donald Trump.