# LLM Bias Detection and Mitigation through the Lens of Desired Distributions

arXiv: https://arxiv.org/abs/2510.06354 · HTML: https://mlsanity.com/paper/2510.06354/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Sustainable Modular Debiasing of Language Models](https://mlsanity.com/paper/2109.03646/) (2021)
- [A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models](https://mlsanity.com/paper/2405.09589/) (2024)
- [A Survey on Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias](https://mlsanity.com/paper/2010.14534/) (2020)
- [Unmasking the Mask -- Evaluating Social Biases in Masked Language Models](https://mlsanity.com/paper/2104.07496/) (2021)
- [Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists](https://mlsanity.com/paper/2203.09192/) (2022)
- [MISGENDERED: Limits of Large Language Models in Understanding Pronouns](https://mlsanity.com/paper/2306.03950/) (2023)
- [Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning](https://mlsanity.com/paper/2306.03350/) (2023)
- [Parameter-efficient Modularised Bias Mitigation via AdapterFusion](https://mlsanity.com/paper/2302.06321/) (2023)
- [BiasEdit: Debiasing Stereotyped Language Models via Model Editing](https://mlsanity.com/paper/2503.08588/) (2025)
- [Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information](https://mlsanity.com/paper/2206.10744/) (2022)
- [Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads](https://mlsanity.com/paper/2311.10395/) (2023)
- [The Impact of Differential Privacy on Group Disparity Mitigation](https://mlsanity.com/paper/2203.02745/) (2022)
- [Effective Controllable Bias Mitigation for Classification and Retrieval using Gate Adapters](https://mlsanity.com/paper/2401.16457/) (2024)
- [PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning](https://mlsanity.com/paper/2409.16722/) (2024)
- [L3iTC at the FinLLM Challenge Task: Quantization for Financial Text Classification & Summarization](https://mlsanity.com/paper/2408.03033/) (2024)

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

- [Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning](https://mlsanity.com/paper/2604.05756/) (2026)
- [Identity-Robust Language Model Generation via Content Integrity Preservation](https://mlsanity.com/paper/2601.09141/) (2026)
- [Effects of Answer Format Variation on Gender Bias in Large Language Models](https://mlsanity.com/paper/2608.17516/) (2026)
- [MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models](https://mlsanity.com/paper/2609.39107/) (2026)

## Abstract (arXiv)

Although prior work on bias mitigation has focused on promoting social equality and demographic parity, less attention has been given to aligning LLM's outputs to desired distributions. For example, we might want to align a model with real-world distributions to support factual grounding. Thus, we define bias as deviation from a desired distribution, which may be an equal or real-world distribution, depending on application goals. We 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. Using 3 profession sets -- male-dominated, female-dominated, and gender-balanced -- derived from U.S. labor statistics (2024), we assess both our adaptive method for reflecting reality and a non-adaptive variant for equality. Across three masked language models, bias is observed under both distributions. We achieve near-complete mitigation under equality and 30-75% reduction under real-world settings. Autoregressive LLMs show no bias under equality but notable bias under real-world settings, with the Llama Instruct models (3.2-3B, 3.1-8B) achieving a 50-62% reduction.