大型语言模型的机器遗忘:基础、进展与智能体扩展
Machine Unlearning for Large Language Models: Foundations, Advances, and Agentic Extensions
浏览论文内容
中文总结 AI 辅助
本综述系统梳理大型语言模型机器遗忘的方法、基准与证据,提出五层框架和七阶段生命周期,并指出当前评估不足以证明外部状态中的移除有效性,需跟踪依赖关系。
中文摘要 AI 辅助
机器遗忘旨在移除目标影响,同时保留其他能力。本综述比较了使用检索、记忆、工具和交互智能体的大型语言模型和系统中的方法、基准和证据。一个五层框架连接了移除请求、系统边界、目标位置、干预措施和支持的主张。一个七阶段生命周期和六个证据维度指导比较。综述表明,目标构建、保留数据和恢复测试会影响报告的结果。来自模型评估的证据仍然不足以证明在外部状态和后续更新中移除的有效性,这促使评估跟踪依赖关系并测试目标影响是否返回。
英文摘要
Machine unlearning aims to remove target influence while preserving other capabilities. This survey compares methods, benchmarks, and evidence across large language models and systems using retrieval, memory, tools, and interacting agents. A five-layer framework connects removal requests, system boundaries, target locations, interventions, and supported claims. A seven-stage lifecycle and six evidence dimensions guide comparison. The review shows that target construction, retained data, and recovery tests affect reported outcomes. Evidence from model evaluations remains insufficient to establish removal across external state and subsequent updates, motivating evaluation that tracks dependencies and tests whether target influence returns.
发表机构
- The Hong Kong Polytechnic University(香港理工大学)
- Southeast University(东南大学)
- Huawei Technologies(华为技术有限公司)
机构由 AI 辅助整理,请以论文原文为准。