mlsanityData to 14 Oct 2026

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

arXiv 2503.13690 ↗First posted 17 Mar 2025cs.CL cs.AI cs.LGcited by 2

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 9 of its 19 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

9 of 19 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning8 Apr

Other references · 8

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  4. 2024OLMo: Accelerating the Science of Language Modelscited by 613
  5. 2024TOFU: A Task of Fictitious Unlearning for LLMscited by 533
  6. 2024On Large Language Model Continual Unlearningcited by 52
  7. 2024Unified Parameter-Efficient Unlearning for LLMscited by 25
  8. 2025LUME: LLM Unlearning with Multitask Evaluationscited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Spacecited by 0
  2. 2026Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
  2. 2025Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
  3. 2024Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
  4. 2025Leveraging Machine Unlearning for Cost-Efficient Preference Alignment
  5. 2024Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
  6. 2025Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
  7. 2025Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs
  8. 2025LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examples