# Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning

arXiv: https://arxiv.org/abs/2504.05632 · HTML: https://mlsanity.com/paper/2504.05632/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [Specializing Smaller Language Models towards Multi-Step Reasoning](https://mlsanity.com/paper/2301.12726/) (2023)
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://mlsanity.com/paper/2212.08061/) (2022)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [Fairness-guided Few-shot Prompting for Large Language Models](https://mlsanity.com/paper/2303.13217/) (2023)
- [Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models](https://mlsanity.com/paper/2405.10431/) (2024)
- [Advancing Reasoning in Large Language Models: Promising Methods and Approaches](https://mlsanity.com/paper/2502.03671/) (2025)
- [Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought](https://mlsanity.com/paper/2403.05518/) (2024)
- [MBIAS: Mitigating Bias in Large Language Models While Retaining Context](https://mlsanity.com/paper/2405.11290/) (2024)
- [Role-Play Paradox in Large Language Models: Reasoning Performance Gains and Ethical Dilemmas](https://mlsanity.com/paper/2409.13979/) (2024)
- [Rethinking Prompt-based Debiasing in Large Language Models](https://mlsanity.com/paper/2503.09219/) (2025)
- [On The Role of Reasoning in the Identification of Subtle Stereotypes in Natural Language](https://mlsanity.com/paper/2308.00071/) (2023)
- [Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws](https://mlsanity.com/paper/2412.11414/) (2024)
- [DR.GAP: Mitigating Bias in Large Language Models using Gender-Aware Prompting with Decoupled Reasoning](https://mlsanity.com/paper/2502.11603/) (2025)

## Built on by (most cited first, 5 of 5)

- [Do Bias Benchmarks Generalise? Evidence from Voice-based Evaluation of Gender Bias in SpeechLLMs](https://mlsanity.com/paper/2510.01254/) (2025)
- [MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion](https://mlsanity.com/paper/2507.02595/) (2025)
- [Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement](https://mlsanity.com/paper/2601.21864/) (2026)
- [BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs](https://mlsanity.com/paper/2608.14161/) (2026)
- [Does Thinking Help Fairness? Reasoning Tokens Resolve Some Biases but Create More](https://mlsanity.com/paper/2609.30768/) (2026)

## Abstract (arXiv)

Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's ability to mitigate stereotypical responses remains largely underexplored. In this work, we investigate the crucial relationship between a model's reasoning ability and fairness, and ask whether improved reasoning capabilities can mitigate harmful stereotypical responses, especially those arising due to shallow or flawed reasoning. We conduct a comprehensive evaluation of multiple open-source LLMs, and find that larger models with stronger reasoning abilities exhibit substantially lower stereotypical bias on existing fairness benchmarks. Building on this insight, we introduce ReGiFT -- Reasoning Guided Fine-Tuning, a novel approach that extracts structured reasoning traces from advanced reasoning models and infuses them into models that lack such capabilities. We use only general-purpose reasoning and do not require any fairness-specific supervision for bias mitigation. Notably, we see that models fine-tuned using ReGiFT not only improve fairness relative to their non-reasoning counterparts but also outperform advanced reasoning models on fairness benchmarks. We also analyze how variations in the correctness of the reasoning traces and their length influence model fairness and their overall performance. Our findings highlight that enhancing reasoning capabilities is an effective, fairness-agnostic strategy for mitigating stereotypical bias caused by reasoning flaws.