# Large Language Models Are Still Misled by Simple Bias Ensembles

arXiv: https://arxiv.org/abs/2505.16522 · HTML: https://mlsanity.com/paper/2505.16522/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 19 of 19)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Sources of Hallucination by Large Language Models on Inference Tasks](https://mlsanity.com/paper/2305.14552/) (2023)
- [Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering](https://mlsanity.com/paper/2309.17249/) (2023)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [Measuring Political Bias in Large Language Models: What Is Said and How It Is Said](https://mlsanity.com/paper/2403.18932/) (2024)
- [Explore Spurious Correlations at the Concept Level in Language Models for Text Classification](https://mlsanity.com/paper/2311.08648/) (2023)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [Evaluating Compositionality in Sentence Embeddings](https://mlsanity.com/paper/1802.04302/) (2018)
- [Social Bias Probing: Fairness Benchmarking for Language Models](https://mlsanity.com/paper/2311.09090/) (2023)
- [UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation](https://mlsanity.com/paper/2405.20612/) (2024)
- [Bias in News Summarization: Measures, Pitfalls and Corpora](https://mlsanity.com/paper/2309.08047/) (2023)
- [Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels](https://mlsanity.com/paper/2309.09697/) (2023)
- [Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models](https://mlsanity.com/paper/2409.17455/) (2024)
- [RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting](https://mlsanity.com/paper/2412.07675/) (2024)

## Abstract (arXiv)

With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that the ensemble of multiple simple biases still exerts a significant adverse impact on LLMs. Given that real-world data samples are typically confounded by a wide range of biases, LLMs tend to exhibit unstable performance when deployed in high-stakes real-world scenarios such as clinical diagnosis and legal document analysis. However, previous benchmarks are constrained to datasets where each sample is manually injected with only one type of bias. To bridge this gap, we propose a multi-bias benchmark where each sample contains multiple types of biases. Experimental results reveal that existing LLMs and debiasing methods perform poorly on this benchmark, highlighting the challenge of eliminating such compounded biases.