Do Large Language Models Reflect Demographic Pluralism in Safety? (2026.findings-eacl)
Copied to clipboard
Usman Naseem, Gautam Siddharth Kashyap, Sushant Kumar Ray, Rafiq Ali, Ebad Shabbir, Abdullah Mohammad
| Challenge: | Existing datasets that focus on demographics and safety are narrow in their annotator pools. |
| Approach: | They propose to decouple value framing from responses by modeling pluralism directly at the prompt level. |
| Outcome: | Demo-SafetyBench decouples value framing from responses to model pluralism at the prompt level. |
Similar Papers
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. |
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)
Copied to clipboard
Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang
| Challenge: | Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours. |
| Approach: | They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs . |
| Outcome: | The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models. |
Safety of Large Language Models Beyond English: A Systematic Literature Review of Risks, Biases, and Safeguards (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have a growing number of applications that generate harmful, biased, or unsafe content. |
| Approach: | They synthesize findings from recent studies that evaluate their robustness across languages . they highlight gaps in multilingual safety research and recommend future work . |
| Outcome: | The systematic review examines the multilingual safety of large language models in English . it identifies challenges such as dataset availability and evaluation biases . |
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. |
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. |
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts (2024.findings-acl)
Copied to clipboard
Lingfeng Shen, Weiting Tan, Sihao Chen, Yunmo Chen, Jingyu Zhang, Haoran Xu, Boyuan Zheng, Philipp Koehn, Daniel Khashabi
| Challenge: | Recent studies show that malicious prompt instructions could solicit objectionable content from LLMs. |
| Approach: | They compare how state-of-the-art LLMs respond to malicious prompts in different languages . they find that LLM's generate unsafe responses more often when a prompt is written in a lower-resource language . |
| Outcome: | The proposed model can generate unsafe responses more often when a malicious prompt is written in a lower-resource language, and less irrelevant responses when written in lower-source languages. |
Missing the Margins: A Systematic Literature Review on the Demographic Representativeness of LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | 211 studies on the demographic representativeness of large language models have conflicting results . 29% of the studies report positive conclusions on the representativeness, 30% do not evaluate LLMs across multiple demographic categories or within demographic subcategories. |
| Approach: | 211 papers review the representativeness of large language models . authors recommend more precise evaluation methods and comprehensive documentation of demographic attributes . |
| Outcome: | 211 studies on the representativeness of large language models are reviewed . 29% of the studies report positive conclusions, but 30% fail to specify subcategories . authors recommend more precise evaluation methods and documentation of demographic attributes . |
Characterizing Selective Refusal Bias in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | a recent study shows that safety guardrails in large language models can inadvertently introduce or reflect new biases as they may refuse to generate harmful content targeting some demographic groups and not others. |
| Approach: | They examine the selective refusal bias in large language models by examining demographics and responses. |
| Outcome: | The proposed model fails to defend against an indirect attack on previously refused groups in 89% of the trials. |
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 . |
From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards (2024.findings-acl)
Copied to clipboard
Khaoula Chehbouni, Megha Roshan, Emmanuel Ma, Futian Wei, Afaf Taik, Jackie Cheung, Golnoosh Farnadi
| Challenge: | Recent advances in large language models have also introduced additional safety risks and raised concerns regarding their detrimental impact on already marginalized populations. |
| Approach: | They propose to use LLMs to evaluate their safety responses on already mitigated biases by evaluating models on already encoded assumptions. |
| Outcome: | The proposed model can encode harmful assumptions, but it can also be harmful for certain demographic groups. |