Zesheng Shi, Yucheng Zhou, Jing Li, Yuxin Jin, Yu Li, Daojing He, Fangming Liu, Saleh Alharbi, Jun Yu, Min Zhang
| Challenge: | Existing defense mechanisms have not fully deleted harmful knowledge in large language models (LLMs) Existing methods to address safety alignment have not completely deleted harmful information in LLMs. |
| Approach: | They propose a safety alignment strategy that uses scoring neurons to identify useful knowledge in LLMs and pruning the gradients of neurons in U to preserve beneficial information. |
| Outcome: | The proposed method significantly improves model safety while maintaining utility compared to existing methods. |
Similar Papers
Unraveling LLM Jailbreaks Through Safety Knowledge Neurons (2026.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved significant progress in alignment, ensuring safer and more reliable outputs. |
| Approach: | They propose a neuron-level interpretability method that focuses on the role of safety-related knowledge neurons to improve model robustness against jailbreak attacks. |
| Outcome: | The proposed method reduces attack success rates across multiple LLMs and outperforms all baseline defenses. |
CAP: Controllable Alignment Prompting for Unlearning in LLMs (2026.acl-long)
Copied to clipboard
Zhaokun Wang, Jinyu Guo, Jingwen Pu, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li, Guangchun Luo, Wenhong Tian
| Challenge: | Existing methods for modifying parameters are unsystematic and rely on empirical experience. |
| Approach: | They propose a controllable alignment prompting for unlearning framework that decouples unlearning into a learnable prompt optimization process via reinforcement learning. |
| Outcome: | The proposed framework achieves precise, controllable unlearning without updating model parameters. |
Can Textual Unlearning Solve Cross-Modality Safety Alignment? (2024.findings-emnlp)
Copied to clipboard
Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael Abu-Ghazaleh, M. Salman Asif, Yue Dong, Amit Roy-Chowdhury, Chengyu Song
| Challenge: | integrating new modalities into large language models creates new attack surface . existing safety training techniques like SFT and RLHF are not feasible in multi-modal settings . |
| Approach: | They explore whether unlearning in the textual domain can be effective for cross-modality safety alignment. |
| Outcome: | The proposed approach reduces the Attack Success Rate (ASR) to less than 8% and preserves the utility. |
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. |
Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. |
| Approach: | They propose a data-level defence that renders text unlearnable to LLMs by injecting carefully designed alignment-triggering disclaimers into the models' alignment mechanisms. |
| Outcome: | The proposed approach exploits the models’ alignment mechanisms to prevent effective learning. |
Towards Safer Large Language Models through Machine Unlearning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing work attempted to implement a gradient ascent based approach to prevent LLMs from producing harmful output when faced with problematic prompts. |
| Approach: | They propose a gradient ascent based approach to prevent LLMs from producing harmful output when faced with problematic prompts. |
| Outcome: | The proposed approach eliminates harmful knowledge while preserving utility on normal prompts. |
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment (2026.findings-acl)
Copied to clipboard
Iago Alves Brito, Walcy Rios, Julia Soares Dollis, Diogo Fernandes Costa Silva, Arlindo Rodrigues Galvão Filho
| Challenge: | Existing safety evaluations of large language models aggregate harms under generic categories such as "Identity Hate" a bilingual benchmark identifies a selective safety trap, where defense rates vary by up to 42% within the same model solely based on the target group. |
| Approach: | They propose a bilingual adversarial benchmark to audit selective safety in large language models . defense rates vary by up to 42% within the same model solely based on target group . |
| Outcome: | The proposed benchmark identifies a selective safety trap in large language models . defense rates vary by up to 42% within the same model solely based on the target group. |
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. |
Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models (2024.naacl-long)
Copied to clipboard
Yi Luo, Zhenghao Lin, YuHao Zhang, Jiashuo Sun, Chen Lin, Chengjin Xu, Xiangdong Su, Yelong Shen, Jian Guo, Yeyun Gong
| Challenge: | Guide-Align is a guideline-oriented approach to augment the safety and quality of Large Language Models. |
| Approach: | They propose a guideline-oriented method to augment the safety and quality of large language models. |
| Outcome: | The proposed method outperforms existing methods on three benchmarks and shows significant improvements in security and quality. |