FROC：一种用于大语言模型机器去学习的统一框架，具有风险优化控制
FROC: A Unified Framework with Risk-Optimized Control for Machine Unlearning in LLMs
AI总结：
FROC提出了一种用于大语言模型机器去学习的统一框架，通过风险优化控制机制，实现对去学习过程的风险管理和效用平衡。
摘要：
机器去学习（MU）旨在消除特定训练示例对部署模型的影响。随着大语言模型（LLMs）被广泛应用，管理因遗忘不足或效用损失导致的风险变得越来越重要。当前的MU技术缺乏有效评估和控制这些风险的机制，阻碍了选择能够平衡安全性和效用性的策略，并引发了对“被遗忘权”的信任问题。为了解决这些问题，我们提出了FROC，一种用于大语言模型机器去学习的统一框架，具有风险优化控制。FROC围绕一种符合性风格的风险控制公式构建，该公式表达了用户指定的去学习行为风险预算。这种基于概率的约束使FROC能够比较MU策略，识别可行的运行区域，并根据希望在遗忘充分性和效用保持之间的权衡来指导超参数选择。为了将这一约束具体化，FROC引入了一个平滑变化的连续风险模型，将遗忘不足和效用退化整合到一个配置层面的分数中。基于符合性风险分析，FROC计算（1）符合性去学习风险（CUR），一个基于数据驱动的估计值，用于估计被遗忘样本继续影响模型预测的概率，以及（2）风险控制的配置集，这些配置集识别在指定风险预算下有效的去学习超参数。在多种LLM去学习方法上的实验表明，FROC产生稳定、可解释的风险景观，并揭示了去学习配置、语义偏移和效用影响之间的一致关系。FROC将MU重新定义为可控、风险意识的过程，并为大规模LLM部署中的去学习行为管理提供了实用的基础。
英文摘要：
Machine unlearning (MU) seeks to eliminate the influence of specific training examples from deployed models. As large language models (LLMs) become widely used, managing risks arising from insufficient forgetting or utility loss is increasingly crucial. Current MU techniques lack effective mechanisms for evaluating and controlling these risks, hindering the selection of strategies that appropriately balance safety and utility, and raising trust concerns surrounding the "right to be forgotten." To address these issues, we propose FROC, a unified framework with Risk-Optimized Control for machine unlearning in LLMs. FROC is built around a conformal-style risk-control formulation that expresses a user-specified risk budget on unlearning behavior. This probability-based constraint enables FROC to compare MU strategies, identify feasible operating regions, and guide hyperparameter selection according to desired trade-offs between forgetting sufficiency and utility preservation. To operationalize this constraint, FROC introduces a smoothly varying continuous risk model that aggregates forgetting deficiency and utility degradation into a single configuration-level score. Building on conformal risk analysis, FROC computes (1) the Conformal Unlearning Risk (CUR), a data-driven estimated value on the probability that forgotten samples continue to influence model predictions, and (2) risk-controlled configuration sets, which identify unlearning hyperparameters that are valid under the specified risk budget. Experiments across multiple LLM MU methods demonstrate that FROC produces stable, interpretable risk landscapes and reveals consistent relationships between unlearning configurations, semantic shift, and utility impact. FROC reframes MU as a controllable, risk-aware process and offers a practical foundation for managing unlearning behavior in large-scale LLM deployments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
