# Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs

arXiv: https://arxiv.org/abs/2505.17217 · HTML: https://mlsanity.com/paper/2505.17217/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models](https://mlsanity.com/paper/2402.13064/) (2024)
- [Disclosure and Mitigation of Gender Bias in LLMs](https://mlsanity.com/paper/2402.11190/) (2024)

## Built on by (most cited first, 4 of 4)

- [MoCo: A One-Stop Shop for Model Collaboration Research](https://mlsanity.com/paper/2601.21257/) (2026)
- [Scaling Participation in Modular AI Systems](https://mlsanity.com/paper/2606.07812/) (2026)
- [Modeling the Mental World for Embodied AI: A Comprehensive Review](https://mlsanity.com/paper/2601.02378/) (2025)
- [Identity-Robust Language Model Generation via Content Integrity Preservation](https://mlsanity.com/paper/2601.09141/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often exhibit gender bias, resulting in unequal treatment of male and female subjects across different contexts. To address this issue, we propose a novel data generation framework that fosters exploratory thinking in LLMs. Our approach prompts models to generate story pairs featuring male and female protagonists in structurally identical, morally ambiguous scenarios, then elicits and compares their moral judgments. When inconsistencies arise, the model is guided to produce balanced, gender-neutral judgments. These story-judgment pairs are used to fine-tune or optimize the models via Direct Preference Optimization (DPO). Experimental results show that our method significantly reduces gender bias while preserving or even enhancing general model capabilities. We will release the code and generated data. We release the code and generated data at: https://github.com/WeiKangda/LLMs-Exploratory-Bias-Mitigation/tree/main.