What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs

[2510.25732] What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2510.25732 (cs) [Submitted on 29 Oct 2025 ( v1 ), last revised 26 Aug 2026 (this version, v2)] Title: What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs Authors: Aakriti Shah , Yifan Hu , Thai Le View PDF HTML (experimental) Abstract: Unlearning in large language models (LLMs) is usually evaluated as whether an "unlearned" fact can be recovered. We instead ask whether a fact's structural entanglement with the rest of a model's knowledge predicts whether it leaks after unlearning, whether this relationship changes systematically, and whether it is causal. Across varied unlearning algorithms (WHP and GA+KL), two domains (both fictional Harry Potter and non-fictional U.S. Senators, 2000-2010), and four models (2.7B-13B parameters), we find that before unlearning, more entangled facts are recalled more often (r = +0.39 to +0.51). WHP weakens this relationship but stays positive (r = +0.16 to +0.33); GA+KL inverts it in every domain and model size (r = -0.14 to -0.25). To our knowledge, this is the first report of this specific reversal in the unlearning literature. To confirm this is causal beyond correlation, we directly manipulate a prompt's entanglement score, holding its content, target model fixed, and show recall moves in the predicted direction and reverses sign under GA+KL in the same direction as the correlational analysis. This manipulation is our central evidence that unlearning acts on the underlying knowledge structure, not just its output. Building on this, we train a predictive model that estimates a prompt's post-unlearning factuality/hallucination profile before unlearning is run, creating a unique way of model auditing in triaging which prompts are likely to leak. Comments: 17 pages, 6 figures, 12 tables Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) ACM classes: I.2.7; I.2.6; I.2.4; G.2.2 Cite as: arXiv:2510.25732 [cs.CL] (or arXiv:2510.25732v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2510.25732 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Aakriti Shah [ view email ] [v1] Wed, 29 Oct 2025 17:37:50 UTC (5,015 KB) [v2] Wed, 26 Aug 2026 19:55:47 UTC (7,135 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2025-10 Change to browse by: cs cs.AI References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs#677442
• Why the Brain Knows More than We Do#721193
• The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators#1118651
• Temporal expectation triggers competition in working memory that leads to forgetting#138350
• Temporal expectation triggers competition in working memory that leads to forgetting#134303