LLM Bias Detection and Mitigation through the Lens of Desired Distributions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work on bias mitigation has focused on promoting social equality and demographic parity, but less attention has been given to aligning LLM’s outputs to desired distributions. |
| Approach: | They propose a weighted adaptive loss based fine-tuning method that aligns LLM’s gender–profession output distribution with the desired distribution while preserving language modeling capability. |
| Outcome: | The proposed method achieves near-complete mitigation under equality and 30–75% reduction under real-world settings. |
Similar Papers
Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that large language models are susceptible to societal biases due to their exposure to human-generated data. |
| Approach: | They propose two strategies to mitigate implicit gender biases in large language models . they create scenarios where implicit gender is present and develop a metric to assess the presence of biase . |
| Outcome: | The proposed methods mitigate implicit biases with self-reflection and fine-tuning. |
Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods focus on single-round inference, but this view is problematic in real-world applications. |
| Approach: | They propose a framework that couples Steering Token Calibration with Semantic Alignment to ensure that LLMs are correctly aligned across gender, race, and sentiment. |
| Outcome: | The proposed framework outperforms baseline methods in achieving precise distributional control in attribute generation tasks. |
Mitigating Gender Bias Amplification in Distribution by Posterior Regularization (2020.acl-main)
Copied to clipboard
| Challenge: | Recent studies show that data-driven machine learning models carry societal biases in the dataset they trained on. |
| Approach: | They propose to calibrate top predictions of a model by injecting corpus-level constraints to ensure that the gender disparity is not amplified. |
| Outcome: | The proposed method can almost remove bias amplification in the distribution with little loss of performance. |
Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception (2025.coling-main)
Copied to clipboard
| Challenge: | Detecting media bias is critical due to the spread of misinformation and disinformation on social media platforms. |
| Approach: | They investigate the presence and nature of bias within large language models and its consequential impact on media bias detection. |
| Outcome: | The proposed debiasing strategies include prompt engineering and model fine-tuning. |
Demographic-Aware Language Model Fine-tuning as a Bias Mitigation Technique (2022.aacl-short)
Copied to clipboard
| Challenge: | In this paper, we analyze the variations in gender and racial biases in BERT-like language models when exposed to different demographic groups. |
| Approach: | They analyze gender and racial biases in BERT-like language models when exposed to different demographic groups. |
| Outcome: | The proposed model can mitigate biases in text authored by disadvantaged demographic groups compared to advantaged groups . the proposed model is agnostic to the language of the speakers behind the language . |
Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks (2026.acl-long)
Copied to clipboard
Miaomiao Li, Hao Chen, Yang Wang, Tingyuan Zhu, Weijia Zhang, Kaijie Zhu, Kam-Fai Wong, Jindong Wang
| Challenge: | Generating synthetic datasets via large language models (LLMs) has emerged as promising approach to improve LLM performance. |
| Approach: | They propose three mitigation strategies to mitigate bias inheritance in LLMs by analyzing real and LLM-augmented data. |
| Outcome: | The proposed methods can work differently on different tasks and biases. |
BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization (2024.acl-srw)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been shown to be effective in complex language tasks, but their potential to perpetuate biases poses significant concerns. |
| Approach: | They propose a new framework employing Direct Preference Optimization to mitigate biases in LLMs. |
| Outcome: | The proposed model outperforms the baseline model on almost all bias benchmarks and achieves better performance than open-source models. |
CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges (2025.acl-long)
Copied to clipboard
| Challenge: | Empirical evaluations of large language models demonstrate that they improve performance in a wide range of tasks. |
| Approach: | They propose a label-free method for mitigating selection bias during inference by reformulating debiasing as an optimization task. |
| Outcome: | The proposed method mitigates selection bias and improves performance compared to existing methods. |
Beyond Performance: Quantifying and Mitigating Label Bias in LLMs (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models exhibit undesirable preference toward predicting certain answers over others, despite their adaptability to diverse tasks. |
| Approach: | They propose a label bias calibration method that outperforms recent calibration approaches for improving performance and mitigating label bias. |
| Outcome: | The proposed method outperforms calibration approaches for improving performance and mitigating label bias. |
Fine-tuning LLMs with Cross-Attention-based Weight Decay for Bias Mitigation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel in natural language processing tasks but often propagate societal biases from their training data, leading to discriminatory outputs. |
| Approach: | They propose a method that modifies the LLM architecture to mitigate bias by adjusting the attention weights of sensitive tokens. |
| Outcome: | The proposed method can handle multiple sensitive attributes and does not require full knowledge of sensitive tokens presented in the dataset. |