# BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization

arXiv: https://arxiv.org/abs/2407.13928 · HTML: https://mlsanity.com/paper/2407.13928/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 10 of 10)

- [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)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [A General Theoretical Paradigm to Understand Learning from Human Preferences](https://mlsanity.com/paper/2310.12036/) (2023)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes](https://mlsanity.com/paper/2402.01981/) (2024)
- [Bias Testing and Mitigation in LLM-based Code Generation](https://mlsanity.com/paper/2309.14345/) (2023)

## Built on by (most cited first, 18 of 18)

- [StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization](https://mlsanity.com/paper/2410.08815/) (2024)
- [Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment](https://mlsanity.com/paper/2501.09620/) (2025)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [Learning to Summarize from LLM-generated Feedback](https://mlsanity.com/paper/2410.13116/) (2024)
- [Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs](https://mlsanity.com/paper/2509.00707/) (2025)
- [Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness](https://mlsanity.com/paper/2603.07368/) (2026)
- [USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot Interactions](https://mlsanity.com/paper/2502.10636/) (2025)
- [BiasFilter: An Inference-Time Debiasing Framework for Large Language Models](https://mlsanity.com/paper/2505.23829/) (2025)
- [Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation](https://mlsanity.com/paper/2412.14050/) (2024)
- [Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs](https://mlsanity.com/paper/2508.16921/) (2025)
- [Self-Debias: Self-correcting for Debiasing Large Language Models](https://mlsanity.com/paper/2604.08243/) (2026)
- [BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses](https://mlsanity.com/paper/2510.00232/) (2025)
- [Can SAEs reveal and mitigate racial biases of LLMs in healthcare?](https://mlsanity.com/paper/2511.00177/) (2025)
- [Detection, Classification, and Mitigation of Gender Bias in Large Language Models](https://mlsanity.com/paper/2506.12527/) (2025)
- [Faithful-Patchscopes: Understanding and Mitigating Model Bias in Hidden Representations Explanation of Large Language Models](https://mlsanity.com/paper/2602.00300/) (2026)
- [Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models](https://mlsanity.com/paper/2502.11559/) (2025)
- [Mitigating LLM biases toward spurious social contexts using direct preference optimization](https://mlsanity.com/paper/2604.02585/) (2026)
- [BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2609.35044/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization (DPO) to mitigate gender, racial, and religious biases in LLM-generated English text. By developing a loss function that favors less biased over biased completions, our approach cultivates a preference for respectful and non-discriminatory language in LLMs. We also contribute a manually designed dataset for training LLMs to recognize and correct biases. This dataset encompasses a diverse range of prompts paired with both biased and unbiased completions. Implementing this approach on the Microsoft Phi-2 model, we demonstrate substantial reductions in biased outputs as our model outperforms the baseline model on almost all bias benchmarks. Our model also achieves better performance compared to other open-source models on most benchmarks. By reducing biases in the language generated by the model, our study marks a significant step towards developing more ethical and socially responsible LLMs. We publicly release BiasDPO dataset on HuggingFace.