Saved in:
Bibliographic Details
Main Authors: Liu, Qin, Wang, Fei, Xiao, Chaowei, Chen, Muhao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.14676
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912417737342976
author Liu, Qin
Wang, Fei
Xiao, Chaowei
Chen, Muhao
author_facet Liu, Qin
Wang, Fei
Xiao, Chaowei
Chen, Muhao
contents Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model (LLM) parametric knowledge with non-preferred features is uniformly blocked to all the users. However, this part of knowledge can be useful to advanced users whose expertise qualifies them to handle these information. The one-size-fits-all alignment mechanism undermines LLM's utility for these qualified users. To address this problem, we propose SudoLM, a framework that lets LLMs learn access control over specific parametric knowledge for users with different credentials via authorization alignment. SudoLM allows authorized users to unlock their access to all the parametric knowledge with an assigned SUDO key while blocking access to non-qualified users. Experiments on two application scenarios demonstrate that SudoLM effectively controls the user's access to the parametric knowledge and maintains its general utility.
format Preprint
id arxiv_https___arxiv_org_abs_2410_14676
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
Liu, Qin
Wang, Fei
Xiao, Chaowei
Chen, Muhao
Computation and Language
Artificial Intelligence
Existing preference alignment is a one-size-fits-all alignment mechanism, where the part of the large language model (LLM) parametric knowledge with non-preferred features is uniformly blocked to all the users. However, this part of knowledge can be useful to advanced users whose expertise qualifies them to handle these information. The one-size-fits-all alignment mechanism undermines LLM's utility for these qualified users. To address this problem, we propose SudoLM, a framework that lets LLMs learn access control over specific parametric knowledge for users with different credentials via authorization alignment. SudoLM allows authorized users to unlock their access to all the parametric knowledge with an assigned SUDO key while blocking access to non-qualified users. Experiments on two application scenarios demonstrate that SudoLM effectively controls the user's access to the parametric knowledge and maintains its general utility.
title SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2410.14676