LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods. Unlearning has emerged as a promising solution, with state-of-the-art(SOTA) methods often following a localize-first, unlearn-second paradigm that targets specific model parameters. However, existing benchmarks evaluate unlearning solely at the output level, leaving open the question of whether unlearning truly erases knowledge from a model's parameters or merely obfuscates it, a concern reinforced by the success of resurfacing attacks. To
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 63%chrisliu298/awesome-llm-unlearning →
- PossiblePossibly related (embedding) · 46%Evaluate a model properly →
- PossiblePossibly related (embedding) · 45%Dataset of permissively licensed code released →
- LinkedLinked via arxiv author · 85%Matteo Boglioni →
“LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning”
- LinkedLinked via arxiv author · 85%Thibault Rousset →
“LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning”
- LinkedLinked via arxiv author · 85%Siva Reddy →
“LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning”
- LinkedLinked via arxiv author · 85%Marius Mosbach →
“LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning”
- LinkedLinked via arxiv author · 85%Verna Dankers →
“LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning”