Measuring and Mitigating Implicit Bias in Large Language Models – Supplementary Code and Data

This repository provides supplementary materials for the research article “Measuring and Mitigating Implicit Bias in Large Language Models: Interdisciplinary Psycho-Linguistic Approaches and Agent-Based Refinement.” Contents include: bias_mitigation_agent.ipynb: Jupyter notebook implementing bias detection and rewriting pipeline using LangGraph. llm_bias_measurement.ipynb: Jupyter notebook for multi-model evaluation and measurement of bias with descriptive statistics. data/: Example Excel files (Agents.xlsx, Generalization.xlsx, Standard.xlsx) used in experiments. README.md: Documentation and usage instructions. requirements.txt: Python dependencies for reproducibility. These resources enable reproducibility of experiments described in the paper.