Papers › Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization

Atyaephyra at SemEval-2025 Task 4: Low-Rank Negative Preference Optimization

17 Mar 2025arXiv:2503.13690archive 2025-07-28

Jan Bronec, Jindřich Helcl

We present a submission to the SemEval 2025 shared task on unlearning sensitive content from LLMs. Our approach employs negative preference optimization using low-rank adaptation. We show that we can utilize this combination to efficiently compute additional regularization terms, which help with unlearning stabilization. The results of our approach significantly exceed the shared task baselines.

PaperPDFCode

Code

XelfXendr/peft_unlearning officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections