# Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs

arXiv: https://arxiv.org/abs/2410.12864 · HTML: https://mlsanity.com/paper/2410.12864/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 40 references that are in the map.
- First posted on arXiv 13 Oct 2024.

## Builds on (most cited first, 30 of 30)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)
- [Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts](https://mlsanity.com/paper/2402.16822/) (2024)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://mlsanity.com/paper/2012.15859/) (2020)
- [A Survey on Fairness in Large Language Models](https://mlsanity.com/paper/2308.10149/) (2023)
- [On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations](https://mlsanity.com/paper/2203.13928/) (2022)
- [Measuring Implicit Bias in Explicitly Unbiased Large Language Models](https://mlsanity.com/paper/2402.04105/) (2024)
- [A Trip Towards Fairness: Bias and De-Biasing in Large Language Models](https://mlsanity.com/paper/2305.13862/) (2023)
- [Choose Your Lenses: Flaws in Gender Bias Evaluation](https://mlsanity.com/paper/2210.11471/) (2022)
- [On the Independence of Association Bias and Empirical Fairness in Language Models](https://mlsanity.com/paper/2304.10153/) (2023)
- [Prompting Fairness: Integrating Causality to Debias Large Language Models](https://mlsanity.com/paper/2403.08743/) (2024)
- [Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes](https://mlsanity.com/paper/2404.04392/) (2024)
- [How Gender Debiasing Affects Internal Model Representations, and Why It Matters](https://mlsanity.com/paper/2204.06827/) (2022)
- [SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming](https://mlsanity.com/paper/2408.11851/) (2024)
- [BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models](https://mlsanity.com/paper/2302.07371/) (2023)

## Built on by (most cited first, 25 of 25)

- [Vision Language Models are Biased](https://mlsanity.com/paper/2505.23941/) (2025)
- [Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges](https://mlsanity.com/paper/2502.08680/) (2025)
- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race](https://mlsanity.com/paper/2506.00253/) (2025)
- [Rethinking LLM Bias Probing Using Lessons from the Social Sciences](https://mlsanity.com/paper/2503.00093/) (2025)
- [The World According to LLMs: How Geographic Origin Influences LLMs' Entity Deduction Capabilities](https://mlsanity.com/paper/2508.05525/) (2025)
- [AccessEval: Benchmarking Disability Bias in Large Language Models](https://mlsanity.com/paper/2509.22703/) (2025)
- [Probing Association Biases in LLM Moderation Over-Sensitivity](https://mlsanity.com/paper/2505.23914/) (2025)
- [Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions](https://mlsanity.com/paper/2509.25539/) (2025)
- [DIF: A Framework for Benchmarking and Verifying Implicit Bias in LLMs](https://mlsanity.com/paper/2505.10013/) (2025)
- ["Amazing, They All Lean Left" -- Analyzing the Political Temperaments of Current LLMs](https://mlsanity.com/paper/2507.08027/) (2025)
- [Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs](https://mlsanity.com/paper/2410.12010/) (2024)
- [The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection](https://mlsanity.com/paper/2509.15896/) (2025)
- [A Cross-Lingual Analysis of Bias in Large Language Models Using Romanian History](https://mlsanity.com/paper/2510.02362/) (2025)
- [From Delegates to Trustees: How Optimizing for Long-Term Interests Shapes Bias and Alignment in LLM](https://mlsanity.com/paper/2510.12689/) (2025)
- [An evaluation of LLMs for political bias in Western media: Israel-Hamas and Ukraine-Russia wars](https://mlsanity.com/paper/2601.06132/) (2026)
- [Redirected, Not Removed: Task-Dependent Stereotyping Reveals the Limits of LLM Alignments](https://mlsanity.com/paper/2604.02669/) (2026)
- [Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning](https://mlsanity.com/paper/2606.26036/) (2026)
- [An Evaluation of LLMs for Detecting Harmful Computing Terms](https://mlsanity.com/paper/2503.09341/) (2025)
- [Who Gets Left Behind? Auditing Disability Inclusivity in Large Language Models](https://mlsanity.com/paper/2509.00963/) (2025)
- [Cross-Modal Content Optimization for Steering Web Agent Preferences](https://mlsanity.com/paper/2510.03612/) (2025)
- [When Harmless Words Harm: A New Threat to LLM Safety via Conceptual Triggers](https://mlsanity.com/paper/2511.21718/) (2025)
- [ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues](https://mlsanity.com/paper/2604.01925/) (2026)
- [SocioEval: A Template-Based Framework for Evaluating Socioeconomic Status Bias in Foundation Models](https://mlsanity.com/paper/2604.02660/) (2026)
- [The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMs](https://mlsanity.com/paper/2609.07117/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) are being adopted across a wide range of tasks, including decision-making processes in industries where bias in AI systems is a significant concern. Recent research indicates that LLMs can harbor implicit biases even when they pass explicit bias evaluations. Building upon the frameworks of the LLM Implicit Association Test (IAT) Bias and LLM Decision Bias, this study highlights that newer or larger language models do not automatically exhibit reduced bias; in some cases, they displayed higher bias scores than their predecessors, such as in Meta's Llama series and OpenAI's GPT models. This suggests that increasing model complexity without deliberate bias mitigation strategies can unintentionally amplify existing biases. The variability in bias scores within and across providers underscores the need for standardized evaluation metrics and benchmarks for bias assessment. The lack of consistency indicates that bias mitigation is not yet a universally prioritized goal in model development, which can lead to unfair or discriminatory outcomes. By broadening the detection of implicit bias, this research provides a more comprehensive understanding of the biases present in advanced models and underscores the critical importance of addressing these issues to ensure the development of fair and responsible AI systems.