# Fantastic Biases (What are They) and Where to Find Them

arXiv: https://arxiv.org/abs/2411.15051 · HTML: https://mlsanity.com/paper/2411.15051/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 51 references that are in the map.
- First posted on arXiv 22 Nov 2024.

## Builds on (most cited first, 17 of 17)

- [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)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Scaling Laws and Interpretability of Learning from Repeated Data](https://mlsanity.com/paper/2205.10487/) (2022)
- [TimeLMs: Diachronic Language Models from Twitter](https://mlsanity.com/paper/2202.03829/) (2022)
- [Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties](https://mlsanity.com/paper/2309.00779/) (2023)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [A Systematic Study of Bias Amplification](https://mlsanity.com/paper/2201.11706/) (2022)
- [Speaking Multiple Languages Affects the Moral Bias of Language Models](https://mlsanity.com/paper/2211.07733/) (2022)
- [The Touch'e23-ValueEval Dataset for Identifying Human Values behind Arguments](https://mlsanity.com/paper/2301.13771/) (2023)
- [BLIND: Bias Removal With No Demographics](https://mlsanity.com/paper/2212.10563/) (2022)
- [How Far Can We Extract Diverse Perspectives from Large Language Models?](https://mlsanity.com/paper/2311.09799/) (2023)
- [On the Scaling Laws of Geographical Representation in Language Models](https://mlsanity.com/paper/2402.19406/) (2024)
- [Classist Tools: Social Class Correlates with Performance in NLP](https://mlsanity.com/paper/2403.04445/) (2024)
- [A Natural Bias for Language Generation Models](https://mlsanity.com/paper/2212.09686/) (2022)

## Abstract (arXiv)

Deep Learning models tend to learn correlations of patterns on huge datasets. The bigger these systems are, the more complex are the phenomena they can detect, and the more data they need for this. The use of Artificial Intelligence (AI) is becoming increasingly ubiquitous in our society, and its impact is growing everyday. The promises it holds strongly depend on their fair and universal use, such as access to information or education for all. In a world of inequalities, they can help to reach the most disadvantaged areas. However, such a universal systems must be able to represent society, without benefiting some at the expense of others. We must not reproduce the inequalities observed throughout the world, but educate these IAs to go beyond them. We have seen cases where these systems use gender, race, or even class information in ways that are not appropriate for resolving their tasks. Instead of real causal reasoning, they rely on spurious correlations, which is what we usually call a bias. In this paper, we first attempt to define what is a bias in general terms. It helps us to demystify the concept of bias, to understand why we can find them everywhere and why they are sometimes useful. Second, we focus over the notion of what is generally seen as negative bias, the one we want to avoid in machine learning, before presenting a general zoology containing the most common of these biases. We finally conclude by looking at classical methods to detect them, by means of specially crafted datasets of templates and specific algorithms, and also classical methods to mitigate them.