# How Robust are LLMs to In-Context Majority Label Bias?

arXiv: https://arxiv.org/abs/2312.16549 · HTML: https://mlsanity.com/paper/2312.16549/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 27 Dec 2023.

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [The Role of the Crowd in Countering Misinformation: A Case Study of the COVID-19 Infodemic](https://mlsanity.com/paper/2011.05773/) (2020)
- [Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning](https://mlsanity.com/paper/2307.15411/) (2023)

## Built on by (most cited first, 14 of 14)

- [On the Noise Robustness of In-Context Learning for Text Generation](https://mlsanity.com/paper/2405.17264/) (2024)
- [Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict](https://mlsanity.com/paper/2506.06485/) (2025)
- [NICE: To Optimize In-Context Examples or Not?](https://mlsanity.com/paper/2402.06733/) (2024)
- [Generative or Discriminative? Revisiting Text Classification in the Era of Transformers](https://mlsanity.com/paper/2506.12181/) (2025)
- [Shortcut Learning in In-Context Learning: A Survey](https://mlsanity.com/paper/2411.02018/) (2024)
- [BiasICL: In-Context Learning and Demographic Biases of Vision Language Models](https://mlsanity.com/paper/2503.02334/) (2025)
- [Incomplete In-context Learning](https://mlsanity.com/paper/2505.07251/) (2025)
- [Template-Based Probes Are Imperfect Lenses for Counterfactual Bias Evaluation in LLMs](https://mlsanity.com/paper/2404.03471/) (2024)
- [Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms](https://mlsanity.com/paper/2509.20278/) (2025)
- [The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers](https://mlsanity.com/paper/2510.16122/) (2025)
- [AMEL: Accumulated Message Effects on LLM Judgments](https://mlsanity.com/paper/2605.22714/) (2026)
- [Exploring Imbalanced Annotations for Effective In-Context Learning](https://mlsanity.com/paper/2502.04037/) (2025)
- [In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification](https://mlsanity.com/paper/2605.08295/) (2026)
- [Label Collapse in Diffusion Language Model In-Context Learning](https://mlsanity.com/paper/2610.16839/) (2026)

## Abstract (arXiv)

In the In-Context Learning (ICL) setup, various forms of label biases can manifest. One such manifestation is majority label bias, which arises when the distribution of labeled examples in the in-context samples is skewed towards one or more specific classes making Large Language Models (LLMs) more prone to predict those labels. Such discrepancies can arise from various factors, including logistical constraints, inherent biases in data collection methods, limited access to diverse data sources, etc. which are unavoidable in a real-world industry setup. In this work, we study the robustness of in-context learning in LLMs to shifts that occur due to majority label bias within the purview of text classification tasks. Prior works have shown that in-context learning with LLMs is susceptible to such biases. In our study, we go one level deeper and show that the robustness boundary varies widely for different models and tasks, with certain LLMs being highly robust (~90%) to majority label bias. Additionally, our findings also highlight the impact of model size and the richness of instructional prompts contributing towards model robustness. We restrict our study to only publicly available open-source models to ensure transparency and reproducibility.