Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.23465 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911461762138112 |
|---|---|
| author | Almheiri, Saeed Kongrat, Yerulan Santosh, Adrian Tasmukhanov, Ruslan Vera, Josemaria Loza Kautsar, Muhammad Dehan Al Koto, Fajri |
| author_facet | Almheiri, Saeed Kongrat, Yerulan Santosh, Adrian Tasmukhanov, Ruslan Vera, Josemaria Loza Kautsar, Muhammad Dehan Al Koto, Fajri |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23465 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Role-Aware Language Models for Secure and Contextualized Access Control in Organizations Almheiri, Saeed Kongrat, Yerulan Santosh, Adrian Tasmukhanov, Ruslan Vera, Josemaria Loza Kautsar, Muhammad Dehan Al Koto, Fajri Computation and Language Artificial Intelligence 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. |
| title | Role-Aware Language Models for Secure and Contextualized Access Control in Organizations |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.23465 |