机器遗忘应以输出风险控制为核心目标
Risk-Aware Output Control Should be the Focus of Machine Unlearning
一篇立场论文，说机器遗忘领域追错了方向：别纠结参数像不像重训模型，该直接保证输出里没毒没泄漏，说得挺有道理。
这篇立场论文针对机器遗忘（Machine Unlearning）研究方向提出批评。作者认为当前主流工作追求参数空间上与重新训练模型不可区分，这一目标与实际用户需求错位。论文主张应转向有统计保证的输出空间控制，即控制模型的偏差、毒性、幻觉和敏感信息泄露等风险。作者用实证证据和已有理论结果支持这一论点。
Risk-Aware Output Control Should be the Focus of Machine Unlearning
Well-documented failure modes of machine learning (ML) systems, including bias, toxicity, hallucination, and leakage of sensitive information, has driven the rise of machine unlearning (MU). Most existing work, however, targets parameter-space indistinguishability, seeking unlearned models that are as close as possible to models retrained from scratch on retained data. In this paper, we argue that this objective is misaligned with practical and user-relevant concerns: MU should prioritize statistically guaranteed output-space control rather than parameter-space similarity. We contend that output control with statistical guarantees is the operationally meaningful notion of unlearning, as it supports rigorous and robust objectives, scales to modern deployment settings, and enables interpretable guarantees. We substantiate this position with empirical evidence and with recent theoretical results that, although not originally formulated in this framing, are consistent with it.