# Role-Aware Language Models for Secure and Contextualized Access Control in Organizations

arXiv: https://arxiv.org/abs/2507.23465 · HTML: https://mlsanity.com/paper/2507.23465/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security.
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Placed in

- LLM safety and security / [Prompt injection and agent security](https://mlsanity.com/safety/prompt-injection-and-agent-security/)

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [MART: Improving LLM Safety with Multi-round Automatic Red-Teaming](https://mlsanity.com/paper/2311.07689/) (2023)
- [Can Language Models be Instructed to Protect Personal Information?](https://mlsanity.com/paper/2310.02224/) (2023)
- [Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective](https://mlsanity.com/paper/2310.19233/) (2023)
- [AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees](https://mlsanity.com/paper/2404.08417/) (2024)
- [IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages](https://mlsanity.com/paper/2506.02573/) (2025)
- [sudoLLM: On Multi-role Alignment of Language Models](https://mlsanity.com/paper/2505.14607/) (2025)
- [Encrypted Prompt: Securing LLM Applications Against Unauthorized Actions](https://mlsanity.com/paper/2503.23250/) (2025)

## Built on by (most cited first, 2 of 2)

- [Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models](https://mlsanity.com/paper/2510.07642/) (2025)
- [Chain-of-Authorization: Embedding authorization into large language models](https://mlsanity.com/paper/2603.22869/) (2026)

## Abstract (arXiv)

As large language models (LLMs) are increasingly deployed in enterprise settings, controlling model behavior based on user roles becomes an essential requirement. Existing safety methods typically assume uniform access and focus on preventing harmful or toxic outputs, without addressing role-specific access constraints. In this work, we investigate whether LLMs can be fine-tuned to generate responses that reflect the access privileges associated with different organizational roles. We explore three modeling strategies: a BERT-based classifier, an LLM-based classifier, and role-conditioned generation. To evaluate these approaches, we construct two complementary datasets. The first is adapted from existing instruction-tuning corpora through clustering and role labeling, while the second is synthetically generated to reflect realistic, role-sensitive enterprise scenarios. We assess model performance across varying organizational structures and analyze robustness to prompt injection, role mismatch, and jailbreak attempts.