Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Models (2025.findings-naacl)
Copied to clipboard
Siyin Wang, Xingsong Ye, Qinyuan Cheng, Junwen Duan, Shimin Li, Jinlan Fu, Xipeng Qiu, Xuanjing Huang
| Challenge: | Recent studies focus on single-modality threats, but this approach fails to address cross-modal safety alignment. |
| Approach: | They propose a safety alignment challenge to evaluate cross-modality safety alignment . they propose 'Safe Inputs but Unsafe Output' to consider safety of single modalities . |
| Outcome: | The proposed safety alignment challenge examines cases where modalities are safe independently but could lead to unsafe outputs when combined. |
Similar Papers
USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)
Copied to clipboard
Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang
| Challenge: | Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations. |
| Approach: | They propose a framework that covers 61 risk categories across four modality interactions to address this gap. |
| Outcome: | The proposed framework covers 61 risk categories across four distinct modality interactions. |
SafeLawBench: Towards Safe Alignment of Large Language Models (2025.findings-acl)
Copied to clipboard
Chuxue Cao, Han Zhu, Jiaming Ji, Qichao Sun, Zhenghao Zhu, Wu Yinyu, Josef Dai, Yaodong Yang, Sirui Han, Yike Guo
| Challenge: | Recent studies indicate that large language models (LLMs) may exhibit risks, including threats to the protection of private data and the generation of hallucinations. |
| Approach: | They propose to evaluate LLMs from a legal perspective using the SafeLawBench benchmark. |
| Outcome: | The proposed framework categorizes safety risks into three levels based on legal standards and includes 24,860 multi-choice questions and 1,106 open-domain question-answering tasks. |
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. |
LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion (2025.acl-long)
Copied to clipboard
| Challenge: | Existing safety alignment methods rely on fine-tuning, which inadvertently leads to the increased complexity and computational resources required. |
| Approach: | They propose a safety re-alignment framework with Low-Rank Safety Subspace Fusison that exploits low-rank safety characteristics of LLMs by constructing a low-ranked projection matrix to extract the principal components of safety vectors. |
| Outcome: | The proposed method exploits low-rank safety subspace of the LLMs and is stable during fine-tuning process and is isolated from the model’s general capabilities. |
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models (2025.findings-acl)
Copied to clipboard
Qin Liu, Chao Shang, Ling Liu, Nikolaos Pappas, Jie Ma, Neha Anna John, Srikanth Doss, Lluis Marquez, Miguel Ballesteros, Yassine Benajiba
| Challenge: | LLaVA-7B demonstrated a decline in safety alignment ability on multi-modal inputs compared to its LLM backbone. |
| Approach: | They propose a method to recover alignment ability from LLM backbone while preserving functional capabilities of VLMs. |
| Outcome: | The proposed framework recovers alignment ability that is inherent in the LLM backbone with minimal impact on fluency and linguistic capabilities of pre-trained VLMs. |
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Current alignment methods struggle with dynamic user intentions and complex objectives, making models vulnerable to harmful content. |
| Approach: | They propose a training-free framework that enhances LLM safety across different scenarios. |
| Outcome: | The proposed framework significantly improves safety measures, reduces over-safety, and maintains model utility, outperforming existing methods in ensuring safe content generation. |
SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing alignment methods struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks. |
| Approach: | They propose a framework for 'S**afety' alignment via e**F**ficient' E**x-Ante-R**easoning that instantiates structured Ex-Ance reasoning and embeds predefined safety rules. |
| Outcome: | The proposed framework enhances safety performance while maintaining usefulness and efficiency. |
Multilingual Blending: Large Language Model Safety Alignment Evaluation with Language Mixture (2025.findings-naacl)
Copied to clipboard
| Challenge: | a range of representative Large Language Models have exhibited remarkable generalization capabilities across numerous downstream tasks. |
| Approach: | They propose a query-response scheme to evaluate the safety alignment of LLMs . they found that multilingual query-responding significantly amplifies the detriment of malicious queries . |
| Outcome: | The proposed scheme improves the safety alignment of state-of-the-art LLMs under multilingual conditions. |
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing surveys focus on interpretation or safety, but safety and understanding are core motivations for interpretation research. |
| Approach: | They propose a framework that connects interpretation methods, enhancements they inform, and tools that operationalize them. |
| Outcome: | The proposed framework summarizes nearly 70 studies at their intersections and concludes with open challenges and future directions. |
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack (2024.acl-long)
Copied to clipboard
| Challenge: | Recent developments in balancing usefulness and safety of large language models raise a critical question . current attacks, especially adversarial ones that manipulate malicious prompts, often aim to manipulate the input . |
| Approach: | They show that LLMs can effectively summarize malicious long documents but often refuse to translate them. |
| Outcome: | The findings highlight a vulnerability in LLMs that can't translate or summarize documents . the study focuses on LLM models, Gemini and GPT-4, which can' be exploited . |