# SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment

arXiv: https://arxiv.org/abs/2410.14676 · HTML: https://mlsanity.com/paper/2410.14676/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)

## Builds on (most cited first, 28 of 28)

- [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 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [A Persona-Based Neural Conversation Model](https://mlsanity.com/paper/1603.06155/) (2016)
- [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://mlsanity.com/paper/2310.05344/) (2023)
- [FaithDial: A Faithful Benchmark for Information-Seeking Dialogue](https://mlsanity.com/paper/2204.10757/) (2022)
- [Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment](https://mlsanity.com/paper/2402.19085/) (2024)
- [Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark](https://mlsanity.com/paper/2305.10036/) (2023)
- [An Emulator for Fine-Tuning Large Language Models using Small Language Models](https://mlsanity.com/paper/2310.12962/) (2023)
- [Controlling Style in Generated Dialogue](https://mlsanity.com/paper/2009.10855/) (2020)
- [Exploring the Boundaries of GPT-4 in Radiology](https://mlsanity.com/paper/2310.14573/) (2023)
- [Open-sourced Dataset Protection via Backdoor Watermarking](https://mlsanity.com/paper/2010.05821/) (2020)
- [Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges](https://mlsanity.com/paper/2409.19993/) (2024)
- [Preference Poisoning Attacks on Reward Model Learning](https://mlsanity.com/paper/2402.01920/) (2024)
- [Affective and Dynamic Beam Search for Story Generation](https://mlsanity.com/paper/2310.15079/) (2023)
- [Monotonic Paraphrasing Improves Generalization of Language Model Prompting](https://mlsanity.com/paper/2403.16038/) (2024)
- [From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification](https://mlsanity.com/paper/2403.06326/) (2024)

## Built on by (most cited first, 8 of 8)

- [Permissioned LLMs: Enforcing Access Control in Large Language Models](https://mlsanity.com/paper/2505.22860/) (2025)
- [sudoLLM: On Multi-role Alignment of Language Models](https://mlsanity.com/paper/2505.14607/) (2025)
- [ACCESS DENIED INC: The First Benchmark Environment for Sensitivity Awareness](https://mlsanity.com/paper/2506.00964/) (2025)
- [Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs](https://mlsanity.com/paper/2603.07452/) (2026)
- [Chain-of-Authorization: Embedding authorization into large language models](https://mlsanity.com/paper/2603.22869/) (2026)
- [Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation](https://mlsanity.com/paper/2605.28597/) (2026)
- [Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs](https://mlsanity.com/paper/2606.21638/) (2026)
- [Whose record is this? Diagnosing and authorizing record use in personalized multimodal models](https://mlsanity.com/paper/2609.04801/) (2026)

## Abstract (arXiv)

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.