# Detecting and Mitigating Bias in LLMs through Knowledge Graph-Augmented Training

arXiv: https://arxiv.org/abs/2504.00310 · HTML: https://mlsanity.com/paper/2504.00310/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [ERNIE: Enhanced Language Representation with Informative Entities](https://mlsanity.com/paper/1905.07129/) (2019)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)

## Built on by (most cited first, 3 of 3)

- [Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics](https://mlsanity.com/paper/2506.12365/) (2025)
- [Toward Revealing Nuanced Biases in Medical LLMs](https://mlsanity.com/paper/2507.21176/) (2025)
- [The role of System 1 and System 2 semantic memory structure in human and LLM biases](https://mlsanity.com/paper/2604.12816/) (2026)

## Abstract (arXiv)

Large language models have revolutionized natural language processing with their surprising capability to understand and generate human-like text. However, many of these models inherit and further amplify the biases present in their training data, raising ethical and fairness concerns. The detection and mitigation of such biases are vital to ensuring that LLMs act responsibly and equitably across diverse domains. This work investigates Knowledge Graph-Augmented Training (KGAT) as a novel method to mitigate bias in LLM. Using structured domain-specific knowledge from real-world knowledge graphs, we improve the understanding of the model and reduce biased output. Public datasets for bias assessment include Gender Shades, Bias in Bios, and FairFace, while metrics such as demographic parity and equal opportunity facilitate rigorous detection. We also performed targeted mitigation strategies to correct biased associations, leading to a significant drop in biased output and improved bias metrics. Equipped with real-world datasets and knowledge graphs, our framework is both scalable and effective, paving the way toward responsible deployment in sensitive and high-stakes applications.