SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment

• URL: http://arxiv.org/abs/2410.14676v1
• Date: Fri, 18 Oct 2024 17:59:51 GMT
• Title: SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
• Authors: Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen,
• Abstract summary: We propose SudoLM, a framework that lets LLMs learn access control over specific parametric knowledge. Experiments on two application scenarios demonstrate that SudoLM effectively controls the user's access to the parametric knowledge and maintains its general utility.
• Score: 51.287157951953226
• License:
• Abstract: 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.

Related papers

• Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering [23.96385393039587]
  Large language models (LLMs) can store a significant amount of factual knowledge in their parameters. LLMs can internally register the signals of knowledge conflict at mid-layers. We propose textscSpARE, a representation engineering method that uses pre-trained sparse auto-encoders.
  arXiv  Detail & Related papers  (2024-10-21T13:30:47Z)
• CUTE: Measuring LLMs' Understanding of Their Tokens [54.70665106141121]
  Large Language Models (LLMs) show remarkable performance on a wide variety of tasks. This raises the question: To what extent can LLMs learn orthographic information? We propose a new benchmark, which features a collection of tasks designed to test the orthographic knowledge of LLMs.
  arXiv  Detail & Related papers  (2024-09-23T18:27:03Z)
• Learning to Ask: When LLMs Meet Unclear Instruction [49.256630152684764]
  Large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone. We evaluate the performance of LLMs tool-use under imperfect instructions, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench. We propose a novel framework, Ask-when-Needed (AwN), which prompts LLMs to ask questions to users whenever they encounter obstacles due to unclear instructions.
  arXiv  Detail & Related papers  (2024-08-31T23:06:12Z)
• Human-Centered LLM-Agent User Interface: A Position Paper [8.675534401018407]
  Large Language Model (LLM) -in-the-loop applications have been shown to effectively interpret the human user's commands. A user mostly ignorant to the underlying tools/systems should be able to work with a LAUI to discover an emergent workflow.
  arXiv  Detail & Related papers  (2024-05-19T13:02:45Z)
• User-LLM: Efficient LLM Contextualization with User Embeddings [23.226164112909643]
  User-LLM is a novel framework that leverages user embeddings to directly contextualize large language models with user history interactions. Our approach achieves significant efficiency gains by representing user timelines directly as embeddings, leading to substantial inference speedups of up to 78.1X.
  arXiv  Detail & Related papers  (2024-02-21T08:03:27Z)
• LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations [26.340786701393768]
  Interpretability tools that offer explanations in the form of a dialogue have demonstrated their efficacy in enhancing users' understanding. Current solutions for dialogue-based explanations, however, often require external tools and modules and are not easily transferable to tasks they were not designed for. We present an easily accessible tool that allows users to chat with any state-of-the-art large language model (LLM) about its behavior.
  arXiv  Detail & Related papers  (2024-01-23T09:11:07Z)
• Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations [50.81844184210381]
  We propose a general paradigm that augments large language models with DOmain-specific KnowledgE to enhance their performance on practical applications, namely DOKE. This paradigm relies on a domain knowledge extractor, working in three steps: 1) preparing effective knowledge for the task; 2) selecting the knowledge for each specific sample; and 3) expressing the knowledge in an LLM-understandable way.
  arXiv  Detail & Related papers  (2023-11-16T07:09:38Z)
• Augmented Large Language Models with Parametric Knowledge Guiding [72.71468058502228]
  Large Language Models (LLMs) have significantly advanced natural language processing (NLP) with their impressive language understanding and generation capabilities. Their performance may be suboptimal for domain-specific tasks that require specialized knowledge due to limited exposure to the related data. We propose the novel Parametric Knowledge Guiding (PKG) framework, which equips LLMs with a knowledge-guiding module to access relevant knowledge.
  arXiv  Detail & Related papers  (2023-05-08T15:05:16Z)
• KGRGRL: A User's Permission Reasoning Method Based on Knowledge Graph Reward Guidance Reinforcement Learning [13.26410704945674]
  We create a Knowledge Graph (KG) of multiple domain cyberspace to provide a standard semantic description of cyberspace. All permissions in cyberspace are represented as nodes, and an agent is trained to find all permissions that user can have according to user's initial permissions and cyberspace KG. The results of the experiments showed that the proposed method can successfully reason about user's permissions and increase the intelligence level of the user's permissions reasoning method.
  arXiv  Detail & Related papers  (2022-05-16T08:28:23Z)
• Federated Learning of User Authentication Models [69.93965074814292]
  We propose Federated User Authentication (FedUA), a framework for privacy-preserving training of machine learning models. FedUA adopts federated learning framework to enable a group of users to jointly train a model without sharing the raw inputs. We show our method is privacy-preserving, scalable with number of users, and allows new users to be added to training without changing the output layer.
  arXiv  Detail & Related papers  (2020-07-09T08:04:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.