Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets (2026.acl-long)
Copied to clipboard
| Challenge: | Existing mitigation strategies focus on reactively addressing jailbreak incidents after safety guardrails have been compromised. |
| Approach: | They investigate the degradation of safety guardrails through the lens of representation similarity between upstream alignment datasets and downstream fine-tuning tasks. |
| Outcome: | The proposed model reduces harmfulness score by 10.33% when compared to baseline models. |
Similar Papers
Multitask-Bench: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis. |
| Approach: | They propose to fine-tune LLMs on benign (non-harmful) data to ensure safe outputs. |
| Outcome: | The proposed model reduces attack success rates across a range of tasks without compromising its usefulness. |
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Fine-tuning large language models for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of original alignments. |
| Approach: | They propose to merge the weights of pre- and post-fine-tuned models to improve safety while enhancing performance. |
| Outcome: | Experiments across different downstream tasks and models validate the method’s practicality and effectiveness. |
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models achieve effective safety alignment at the time of release, but fine-tuning often compromises safety mechanisms. |
| Approach: | They propose a method that performs safety realignment for large language models . they identify unsafe delta parameters from the fine-tuned models and recalibrate the retained parameters . |
| Outcome: | The proposed method improves safety performance on safety benchmarks and jailbreak attacks while maintaining their performance on downstream tasks. |
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that fine-tuning with benign data can compromise safety of aligned LLMs. |
| Approach: | They propose a Layer-Aware Representation Filtering method that detects safety-degrading layers within the LLM and leverages their representations to detect them. |
| Outcome: | The proposed method can detect safety-degrading features in benign data and remove them from the model. |
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have sparked concerns about their safety. |
| Approach: | They propose a method to identify safety-related information in the model parameter space . they propose to use a few adversarially chosen examples to fine-tune LLMs . |
| Outcome: | The proposed method can break safety alignment in multilingual LLMs using a few examples . it also shows that the proposed method jailbreaks LLM models adapted to new languages . |
On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)
Copied to clipboard
Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu
| Challenge: | Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited. |
| Approach: | They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO). |
| Outcome: | The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness. |
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) rely on safety alignment to avoid malicious user inputs. |
| Approach: | They employ weak classifiers to explain LLM safety through the intermediate hidden states. |
| Outcome: | The proposed model can identify malicious and normal inputs and detect malicious ones without jailbreak. |
Why Safeguarded Ships Run Aground? Aligned Large Language Models’ Safety Mechanisms Tend to Be Anchored in The Template Region (2025.acl-long)
Copied to clipboard
| Challenge: | Infilling a fixed template between the input instruction and initial model output is a common practice for existing LLMs, but it is vulnerable to inference-time jailbreak attacks. |
| Approach: | They propose to fill a fixed template between the input instruction and initial model output and to detach safety mechanisms from the template region to mitigate the risk of inference-time jailbreak attacks. |
| Outcome: | The proposed method is widespread across aligned LLMs and shows that it mitigates inference-time jailbreak vulnerabilities. |
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race? (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have focused on the models, neglecting the full deployment pipeline . previous studies have underestimated the practical success of these attacks . |
| Approach: | They evaluate the effectiveness of jailbreak attacks targeting LLM safety alignment . they highlight critical gaps and call for further refinement of detection accuracy and usability . |
| Outcome: | The proposed attacks can detect at least one safety filter across the entire deployment pipeline. |
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical prompts. |
| Approach: | They propose a lightweight framework that restores safety while maintaining downstream performance. |
| Outcome: | The proposed framework reduces harmful outputs compared to other defenses, with negligible impact on utility. |