Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei
| Challenge: | Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles. |
| Approach: | They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices . |
| Outcome: | The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts. |
Similar Papers
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. |
Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Yeonjun In, Wonjoong Kim, Kanghoon Yoon, Sungchul Kim, Mehrab Tanjim, Sangwu Park, Kibum Kim, Chanyoung Park
| Challenge: | Extensive benchmarks evaluate LLM safety relying heavily on general standards . no benchmark datasets exist to evaluate the user-specific safety of LLMs . |
| Approach: | a new benchmark is designed to assess user-specific aspect of LLM safety . authors propose a simple remedy based on chain-of-thought to improve user-specified safety. |
| Outcome: | a new benchmark assesses the user-specific aspect of LLM safety . the proposed solution improves user-specified safety by chain-of-thought . |
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. |
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches fail to fully capture all risks in tool utilization, resulting in financial loss or privacy leaking. |
| Approach: | They propose a framework to assess the safety of LLM tool utilization in a prospective manner, covering malicious user instructions and diverse practical toolsets. |
| Outcome: | The proposed framework significantly enhances LLMs’ self-awareness, enabling a more safer and trustworthy tool utilization. |
Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing safety evaluations rely on artificial images to evaluate vision-language models . a recent study found that memes are more effective at bypassing safety measures than synthetic or typographic images. |
| Approach: | They propose a benchmark pairing meme images with harmful and benign instructions . they assess multiple VLMs across single and multi-turn interactions . |
| Outcome: | The proposed benchmark pairs real meme images with harmful and benign instructions. |
Dynamic Evaluation for Oversensitivity in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks rely on static datasets that degrade over time as models evolve, leading to data contamination and diminished evaluative power. |
| Approach: | They construct a framework that generates model-specific challenging datasets and aggregates them across diverse LLM families. |
| Outcome: | The framework captures emerging defensive patterns and aligns with each model’s unique behavior. |
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. |
A Chinese Dataset for Evaluating the Safeguards in Large Language Models (2024.findings-acl)
Copied to clipboard
Yuxia Wang, Zenan Zhai, Haonan Li, Xudong Han, Shom Lin, Zhenxuan Zhang, Angela Zhao, Preslav Nakov, Timothy Baldwin
| Challenge: | a recent study has shown that large language models can produce harmful responses, exposing users to unexpected risks. |
| Approach: | They propose a dataset for the safety evaluation of Chinese LLMs in Mandarin Chinese . they extend the dataset to better identify false negative and false positive examples . |
| Outcome: | The proposed dataset is for the safety evaluation of Chinese LLMs, and is based on a Chinese dataset. |
LongSafety: Evaluating Long-Context Safety of Large Language Models (2025.acl-long)
Copied to clipboard
Yida Lu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Cunxiang Wang, Xiaotao Gu, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating long sequences. |
| Approach: | They propose a benchmark to evaluate LLM safety in open-ended long-context tasks . they find that relevant context and extended input sequences can exacerbate safety risks . |
| Outcome: | The proposed benchmark identifies significant safety vulnerabilities in 16 LLMs . strong safety performance in short-context scenarios does not correlate with safety in long-contact tasks . |
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) often refuse to answer legitimate queries, causing models to treat many reasonable prompts as potentially risky. |
| Approach: | They propose a framework that automatically generates and selects overrefusal prompts near the safety boundary. |
| Outcome: | The proposed framework identifies and curates boundary-aligned prompts, enabling more effective and targeted mitigation of overrefusal. |