Lacuna: Testing if LLM Unlearning Truly Erases Data
sivareddyg · x · 2026-07-04
This paper introduces Lacuna, a testing platform designed to evaluate the local precision of LLM unlearning. The core argument is that unlearning should genuinely erase knowledge rather than merely obfuscate it. This benchmark is used to verify whether unlearning methods actually delete the targeted information.
More from Research
- Causal-only attention for non-generative tasks is wasteful, argues HF engineer — antoine_chaffin · 2026-09-11
- Catholic University of Chile researcher: scaling AI feedback is key to sustainable medical education — julianvarascom · 2026-09-11
- Nature paper images cellular activity across all organs, revealing body-wide circuits — arjunrajlab · 2026-09-11
- SignNet 1M Dataset Released for Sign Language Research — ducha_aiki · 2026-09-11
- ECCV26 Oral: Flow Matching Enables Single-Stage Multi-View Point Cloud Registration — ducha_aiki · 2026-09-11
- InFlux++ Method Released — ducha_aiki · 2026-09-11