# Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching

arXiv: https://arxiv.org/abs/2405.13820 · HTML: https://mlsanity.com/paper/2405.13820/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 55 of its 84 references that are in the map.
- First posted on arXiv 22 May 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 55)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)

## Built on by (most cited first, 17 of 17)

- [Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations](https://mlsanity.com/paper/2406.11801/) (2024)
- [To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models](https://mlsanity.com/paper/2407.01920/) (2024)
- [Dissecting Fine-Tuning Unlearning in Large Language Models](https://mlsanity.com/paper/2410.06606/) (2024)
- [Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture](https://mlsanity.com/paper/2407.07342/) (2024)
- [Locking Down the Finetuned LLMs Safety](https://mlsanity.com/paper/2410.10343/) (2024)
- [RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards](https://mlsanity.com/paper/2506.07736/) (2025)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing](https://mlsanity.com/paper/2507.21084/) (2025)
- [When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents](https://mlsanity.com/paper/2601.17887/) (2026)
- [Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment](https://mlsanity.com/paper/2603.11388/) (2026)
- [Recent Advances in Attack and Defense Approaches of Large Language Models](https://mlsanity.com/paper/2409.03274/) (2024)
- [Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks](https://mlsanity.com/paper/2511.22047/) (2025)
- [The Construction of Instruction-tuned LLMs for Finance without Instruction Data Using Continual Pretraining and Model Merging](https://mlsanity.com/paper/2409.19854/) (2024)
- [The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models](https://mlsanity.com/paper/2505.12287/) (2025)
- [Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding](https://mlsanity.com/paper/2604.17132/) (2026)
- [Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic](https://mlsanity.com/paper/2502.01015/) (2025)
- [Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction](https://mlsanity.com/paper/2605.18104/) (2026)

## Abstract (arXiv)

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses, exhibit over-safety by rejecting safe user inputs, and fail to preserve general utility after safety alignment. To this end, we propose a novel post safety alignment (PSA) method to address these inherent and emerging safety challenges, including safety enhancement, over-safety mitigation, and utility preservation. In specific, we introduce textscSafePatching, a novel framework for comprehensive PSA, where two distinct safety patches are developed on the harmful data to enhance safety and mitigate over-safety concerns, and then seamlessly integrated into the target LLM backbone without compromising its utility. Extensive experiments on four representative aligned LLMs, including LLaMA-2/3, Gemma and Mistral, show that textscSafePatching achieves a more comprehensive PSA than baseline methods, further optimizing the balance between being helpful and harmless in current aligned LLMs. Also, textscSafePatching demonstrates its superiority in continual PSA scenarios.