# Identity-Robust Language Model Generation via Content Integrity Preservation

arXiv: https://arxiv.org/abs/2601.09141 · HTML: https://mlsanity.com/paper/2601.09141/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 29 of 29)

- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting](https://mlsanity.com/paper/2309.07034/) (2023)
- [Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes](https://mlsanity.com/paper/2402.01981/) (2024)
- [Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval](https://mlsanity.com/paper/2407.20371/) (2024)
- [Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models](https://mlsanity.com/paper/2405.10431/) (2024)
- [Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context](https://mlsanity.com/paper/2406.05972/) (2024)
- [Who's asking? User personas and the mechanics of latent misalignment](https://mlsanity.com/paper/2406.12094/) (2024)
- [UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation](https://mlsanity.com/paper/2405.20612/) (2024)
- [LLMs are Biased Teachers: Evaluating LLM Bias in Personalized Education](https://mlsanity.com/paper/2410.14012/) (2024)
- [Exploring Safety-Utility Trade-Offs in Personalized Language Models](https://mlsanity.com/paper/2406.11107/) (2024)
- [Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization](https://mlsanity.com/paper/2505.16467/) (2025)
- [Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs](https://mlsanity.com/paper/2404.10160/) (2024)
- [Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race](https://mlsanity.com/paper/2506.00253/) (2025)
- [Filter bubbles and affective polarization in user-personalized large language model outputs](https://mlsanity.com/paper/2311.14677/) (2023)
- [The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects](https://mlsanity.com/paper/2402.11089/) (2024)
- [Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases](https://mlsanity.com/paper/2502.05849/) (2025)
- [Mitigating Biases in Language Models via Bias Unlearning](https://mlsanity.com/paper/2509.25673/) (2025)
- [The Generation Gap: Exploring Age Bias in the Value Systems of Large Language Models](https://mlsanity.com/paper/2404.08760/) (2024)
- [Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms](https://mlsanity.com/paper/2503.04372/) (2025)
- [On the Mutual Influence of Gender and Occupation in LLM Representations](https://mlsanity.com/paper/2503.06792/) (2025)
- [Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs](https://mlsanity.com/paper/2505.17217/) (2025)
- [LLM Bias Detection and Mitigation through the Lens of Desired Distributions](https://mlsanity.com/paper/2510.06354/) (2025)
- [Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification](https://mlsanity.com/paper/2504.14212/) (2025)

## Built on by (most cited first, 1 of 1)

- [Mitigating LLM biases toward spurious social contexts using direct preference optimization](https://mlsanity.com/paper/2604.02585/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) outputs often vary across user sociodemographic attributes, leading to disparities in factual accuracy, utility, and safety, even for objective questions where demographic information is irrelevant. Unlike prior work on stereotypical or representational bias, this paper studies identity-dependent degradation of core response quality. We show empirically that such degradation arises from biased generation behavior, despite factual knowledge being robustly encoded across identities. Motivated by this mismatch, we propose a lightweight, training-free framework for identity-robust generation that selectively neutralizes non-critical identity information while preserving semantically essential attributes, thus maintaining output content integrity. Experiments across four benchmarks and 18 sociodemographic identities demonstrate an average 77% reduction in identity-dependent bias compared to vanilla prompting and a 45% reduction relative to prompt-based defenses. Our work addresses a critical gap in mitigating the impact of user identity cues in prompts on core generation quality.