越熱門，越難忘：用於大型語言模型遺忘的自適應流行度

摘要

在預訓練期間，常見事實被記憶得更深入，且比稀有事實更難被移除；然而現有的LLM遺忘方法無論訓練資料頻率如何，都施加統一的梯度壓力。我們提出AdaPop（自適應流行度）方法，該方法結合局部詞元置信度與從外部代理（例如維基數據站點連結、LLM作為評審）推導出的依事實流行度而定的指數，並透過對偶上升控制器自動調整遺忘-保留平衡，該控制器每個epoch調整保留懲罰。在三個模型家族和兩個基準測試中，AdaPop在改寫查詢下洩漏的已遺忘內容比競爭方法少約5倍，在對抗性重構下少約1.6倍。我們以內部指標支持我們的分析：在我們的方法下，遺忘集的隱藏狀態比在其他方法下更遠離遺忘前模型的狀態，而保留集的表徵則與遺忘前模型的狀態保持接近。

English

Popular facts are memorised more deeply during pretraining and resist removal longer than rare ones, yet existing LLM unlearning methods apply uniform gradient pressure regardless of training-data frequency. We propose the AdaPop (Adaptive Popularity) method, which combines local token confidence with a per-fact popularity-dependent exponent derived from an external proxy (e.g., Wikidata sitelinks, LLM-as-Judge), and automates the forget-retain balance via a dual-ascent controller that adjusts the retain penalty each epoch. Across three model families and two benchmarks, AdaPop leaks ~5x less forgotten content than competing methods under paraphrased queries and ~1.6x less under adversarial reformulations. We support our analysis with internal metrics: under our method, forget-set hidden states move further from the pre-unlearning model's states than under other methods, while retain-set representations remain close.