mlsanityData to 14 Oct 2026

Enhancing AI Safety Through the Fusion of Low Rank Adapters

arXiv 2501.06208 ↗First posted 30 Dec 2024cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with malicious prompts. In this paper, we explore Low-Rank Adapter Fusion (LoRA) as a means to mitigate these risks while preserving the model's ability to handle diverse instructions effectively. Through an extensive comparative analysis against established baselines using recognized benchmark datasets, we demonstrate a 42% reduction in the harmfulness rate by leveraging LoRA fusion between a task adapter and a safety adapter, the latter of which is specifically trained on our safety dataset. However, we also observe exaggerated safety behaviour, where the model rejects safe prompts that closely resemble unsafe ones

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 30 Dec 2024.

Builds on

18 of 23 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  6. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  7. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  8. 2017Deep reinforcement learning from human preferencescited by 3,912
  9. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  10. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  11. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  12. 2024The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructionscited by 493
6 more
  1. 2023Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructionscited by 387
  2. 2024Mixture of LoRA Expertscited by 181
  3. 2023Removing RLHF Protections in GPT-4 via Fine-Tuningcited by 171
  4. 2023Composing Parameter-Efficient Modules with Arithmetic Operationscited by 156
  5. 2024Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Modelscited by 125
  6. 2023Mechanistically analyzing the effects of fine-tuning on procedurally defined taskscited by 115

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuningcited by 11
  2. 2025Gradient Surgery for Safe LLM Fine-Tuningcited by 11
  3. 2026Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sinkcited by 4
  4. 2025Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approachcited by 2