REVIEW 8 cited by
Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Aligned language models face a significant limitation as their fine-tuning often results in compromised safety. To tackle this, we propose a simple method RESTA that performs LLM safety realignment. RESTA stands for REstoring Safety through Task Arithmetic. At its core, it involves a simple arithmetic addition of a safety vector to the weights of the compromised model. We demonstrate the effectiveness of RESTA in both parameter-efficient and full fine-tuning, covering a wide range of downstream tasks, including instruction following in Chinese, English, and Hindi, as well as problem-solving capabilities in Code and Math. We also showcase the generalizability of RESTA on three existing safety evaluation benchmarks and a multilingual benchmark dataset proposed as a part of this work, consisting of 550 harmful questions covering 11 categories, each with 5 sub-categories of harm. Overall, RESTA decreases the harmfulness of the compromised model from 18.6% to 5.1% and from 9.2% to 1.5% in parameter-efficient and full fine-tuning, respectively, while maintaining most of the model's performance on the task. We release the source codes at: https://github.com/declare-lab/resta.
Forward citations
Cited by 8 Pith papers
-
Understanding Refusal in Language Models with Sparse Autoencoders
Refusal in Gemma-2-2B and Llama-3.1-8B is mediated by a small set of SAE features, harm features causally activate refusal features, and adversarial jailbreaks suppress those refusal features.
-
MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security
MoGUv2 embeds small routers in the deeper layers of LLMs to dynamically blend a helpful variant and a refusal variant, improving safety against jailbreak and fine-tuning attacks while preserving usability.
-
Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint
ProCon anchors each sample's hidden-state projection onto the LLM's initial refusal direction during instruction fine-tuning, reducing refusal-direction drift and safety risks with limited task-performance loss.
-
Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
ROSI bakes the refusal direction into a model's weight matrices via a rank-one update, raising refusal and jailbreak robustness with minimal measured utility cost.
-
SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for LLM Software Systems
A LoRA-adapted SeaLLM model detects unsafe and jailbreak prompts in nine Southeast Asian languages with 97% recall and 98% F1 on the authors' new SEALSBench benchmark, far above zero-shot LlamaGuard.
-
Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers
A stacked-cipher jailbreak with adaptive code selection achieves 80.8% to 100% attack success on commercial large reasoning models.
-
SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs
SafeSteer uses category-specific activation vectors to steer LLMs toward safe, on-topic, non-refusing responses at inference time.
-
Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models
Backdoor fingerprints trained into LoRA adapters on a base LLM transfer to derivative models with 100% trigger success and, in several scenarios, greater robustness than directly injected fingerprints.
Discussion (0). Sign in to comment.