Hugging Face Daily Papers · · 4 min read

The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

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.</p>\n","updatedAt":"2026-08-20T08:17:12.212Z","author":{"_id":"662f8d645c4db70c77a203b0","avatarUrl":"/avatars/72f9a3c39b3ba5114388d16a35524835.svg","fullname":"Elena Tutubalina","name":"tlenusik","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8573484420776367},"editors":["tlenusik"],"editorAvatarUrls":["/avatars/72f9a3c39b3ba5114388d16a35524835.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.14229","authors":[{"_id":"6a86b6c6db13816030683fd9","name":"Anna Borisiuk","hidden":false},{"_id":"6a86b6c6db13816030683fda","name":"Andrey Savchenko","hidden":false},{"_id":"6a86b6c6db13816030683fdb","name":"Alexander Panchenko","hidden":false},{"_id":"6a86b6c6db13816030683fdc","user":{"_id":"662f8d645c4db70c77a203b0","avatarUrl":"/avatars/72f9a3c39b3ba5114388d16a35524835.svg","isPro":false,"fullname":"Elena Tutubalina","user":"tlenusik","type":"user","name":"tlenusik"},"name":"Elena Tutubalina","status":"claimed_verified","statusLastChangedAt":"2026-08-20T08:45:04.904Z","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/662f8d645c4db70c77a203b0/HfCCyICcC1Ueyr9-tSvOr.jpeg"],"publishedAt":"2026-08-14T00:00:00.000Z","submittedOnDailyAt":"2026-08-20T00:00:00.000Z","title":"The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning","submittedOnDailyBy":{"_id":"662f8d645c4db70c77a203b0","avatarUrl":"/avatars/72f9a3c39b3ba5114388d16a35524835.svg","isPro":false,"fullname":"Elena Tutubalina","user":"tlenusik","type":"user","name":"tlenusik"},"summary":"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.","upvotes":3,"discussionId":"6a86b6c6db13816030683fdd","ai_summary":"AdaPop adapts gradient pressure by fact popularity and automates forget-retain balance to reduce leakage of unlearned content.","ai_keywords":["AdaPop","local token confidence","per-fact popularity-dependent exponent","dual-ascent controller","forget-retain balance","hidden states"],"ai_summary_model":"thinkingmachines/Inkling-Small"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"641b83837c21ab946bf50cc5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/641b83837c21ab946bf50cc5/SW-yrQiNsg9N8MHsP-tZ9.jpeg","isPro":false,"fullname":"Sweetie Paws","user":"SwetieePawsss","type":"user"},{"_id":"662f8d645c4db70c77a203b0","avatarUrl":"/avatars/72f9a3c39b3ba5114388d16a35524835.svg","isPro":false,"fullname":"Elena Tutubalina","user":"tlenusik","type":"user"},{"_id":"60cd95ee15ecba5f2200304a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60cd95ee15ecba5f2200304a/3gMYeWm8wQO5KfqE5RmEe.jpeg","isPro":false,"fullname":"Alexey Dontsov","user":"therem","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.14229.md","query":{}}">
Papers
arxiv:2608.14229

The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning

Published on Aug 14
· Submitted by
Elena Tutubalina
on Aug 20
Authors:
,

Abstract

AdaPop adapts gradient pressure by fact popularity and automates forget-retain balance to reduce leakage of unlearned content.

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.

Community

Paper author Paper submitter about 2 hours ago

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.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2608.14229
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper

No model linking this paper

Cite arxiv.org/abs/2608.14229 in a model README.md to link it from this page.

Datasets citing this paper

No dataset linking this paper

Cite arxiv.org/abs/2608.14229 in a dataset README.md to link it from this page.

Spaces citing this paper

No Space linking this paper

Cite arxiv.org/abs/2608.14229 in a Space README.md to link it from this page.

Collections including this paper

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers