# PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)

arXiv: https://arxiv.org/abs/2507.02966 · HTML: https://mlsanity.com/paper/2507.02966/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 63 references that are in the map.
- First posted on arXiv 30 Jun 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [A Survey on Deep Learning for Named Entity Recognition](https://mlsanity.com/paper/1812.09449/) (2018)
- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [SpanNER: Named Entity Re-/Recognition as Span Prediction](https://mlsanity.com/paper/2106.00641/) (2021)
- [SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning](https://mlsanity.com/paper/2004.11246/) (2020)
- [Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment](https://mlsanity.com/paper/2302.10908/) (2023)
- [Large Language Models are Advanced Anonymizers](https://mlsanity.com/paper/2402.13846/) (2024)
- [Bias in Multimodal AI: Testbed for Fair Automatic Recruitment](https://mlsanity.com/paper/2004.07173/) (2020)
- [edBB-Demo: Biometrics and Behavior Analysis for Online Educational Platforms](https://mlsanity.com/paper/2211.09210/) (2022)
- [Leveraging Large Language Models for Topic Classification in the Domain of Public Affairs](https://mlsanity.com/paper/2306.02864/) (2023)
- [Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics](https://mlsanity.com/paper/2402.09225/) (2024)
- [Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment](https://mlsanity.com/paper/2506.11880/) (2025)
- [IFBiD: Inference-Free Bias Detection](https://mlsanity.com/paper/2109.04374/) (2021)
- [Measuring Bias in AI Models: An Statistical Approach Introducing N-Sigma](https://mlsanity.com/paper/2304.13680/) (2023)
- [Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs](https://mlsanity.com/paper/2503.07384/) (2025)
- [Toward Face Biometric De-identification using Adversarial Examples](https://mlsanity.com/paper/2302.03657/) (2023)
- [FairCVtest Demo: Understanding Bias in Multimodal Learning with a Testbed in Fair Automatic Recruitment](https://mlsanity.com/paper/2009.07025/) (2020)
- [AI-based Multimodal Biometrics for Detecting Smartphone Distractions: Application to Online Learning](https://mlsanity.com/paper/2506.17364/) (2025)
- [SaFL: Sybil-aware Federated Learning with Application to Face Recognition](https://mlsanity.com/paper/2311.04346/) (2023)
- [Blockchain and Biometrics: Survey, GDPR Analysis, and Future Directions](https://mlsanity.com/paper/2302.10883/) (2023)

## Built on by (most cited first, 11 of 11)

- [AttZoom: Attention Zoom for Better Visual Features](https://mlsanity.com/paper/2508.03625/) (2025)
- [Auditing Training Data in Domain-adapted LLMs: LoRA-MINT](https://mlsanity.com/paper/2606.06946/) (2026)
- [Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond](https://mlsanity.com/paper/2607.02197/) (2026)
- [Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning](https://mlsanity.com/paper/2509.07879/) (2025)
- [Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering](https://mlsanity.com/paper/2607.07179/) (2026)
- [Exploring Vision-Language Models for Online Signature Verification: A Zero-Shot Capability Study](https://mlsanity.com/paper/2605.14845/) (2026)
- [CrimeNER Demo: Named-Entity Recognition in the Crime Domain](https://mlsanity.com/paper/2607.14800/) (2026)
- [AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanations](https://mlsanity.com/paper/2607.25634/) (2026)
- [GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalation](https://mlsanity.com/paper/2608.29251/) (2026)
- [PrivBench: A Holistic and Modular Benchmarking Platform for Evaluating Text-to-Text Privatization](https://mlsanity.com/paper/2608.29624/) (2026)
- [inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs](https://mlsanity.com/paper/2610.18051/) (2026)

## Abstract (arXiv)

The use of Natural Language Processing (NLP) in highstakes AI-based applications has increased significantly in recent years, especially since the emergence of Large Language Models (LLMs). However, despite their strong performance, LLMs introduce important legal/ ethical concerns, particularly regarding privacy, data protection, and transparency. Due to these concerns, this work explores the use of Named- Entity Recognition (NER) to facilitate the privacy-preserving training (or adaptation) of LLMs. We propose a framework that uses NER technologies to anonymize sensitive information in text data, such as personal identities or geographic locations. An evaluation of the proposed privacy-preserving learning framework was conducted to measure its impact on user privacy and system performance in a particular high-stakes and sensitive setup: AI-based resume scoring for recruitment processes. The study involved two language models (BERT and RoBERTa) and six anonymization algorithms (based on Presidio, FLAIR, BERT, and different versions of GPT) applied to a database of 24,000 candidate profiles. The findings indicate that the proposed privacy preservation techniques effectively maintain system performance while playing a critical role in safeguarding candidate confidentiality, thus promoting trust in the experimented scenario. On top of the proposed privacy-preserving approach, we also experiment applying an existing approach that reduces the gender bias in LLMs, thus finally obtaining our proposed Privacyand Bias-aware LLMs (PBa-LLMs). Note that the proposed PBa-LLMs have been evaluated in a particular setup (resume scoring), but are generally applicable to any other LLM-based AI application.