BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap

ICLR 2026 Conference Submission17028 Authors

Keywords: Unlearning, LLM, benchmark

Abstract: Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning involves balancing between forget quality (effectively unlearning undesirable information) and retain quality (maintaining good performance on other, general tasks). Unfortunately, as we show, current LLM unlearning benchmarks contain highly disparate forget and retain sets---painting a false picture of the effectiveness of LLM unlearning methods. This can be particularly problematic because it opens the door for benign perturbations, such as relearning attacks, to easily reveal supposedly unlearned knowledge once models are deployed. To address this, we present BLUR: a benchmark for LLM unlearning that provides more realistic scenarios of forget-retain overlap. BLUR significantly expands on existing unlearning benchmarks by providing extended evaluation tasks, combined forget/retain queries, and relearning datasets of varying degrees of difficulty. Despite the benign nature of the queries considered, we find that the performance of existing methods drops significantly when evaluated on BLUR, with simple approaches performing better on average than more recent methods. These results highlight the importance of robust evaluation and suggest several important directions of future study.

Primary Area: datasets and benchmarks

Submission Number: 17028