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. |
Similar Papers
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. |
PURE: Aligning LLM via Pluggable Query Reformulation for Enhanced Helpfulness (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) depend on vast amounts of text data sourced from the Internet for their training. |
| Approach: | They propose a new alignment paradigm that reformulates risky queries into highly relevant yet harmless ones before feeding them into LLMs. |
| Outcome: | The proposed approach eliminates the high costs of training base LLMs and achieves a promising balance of harmlessness and helpfulness. |
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. |
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. |
Safer-Instruct: Aligning Language Models with Automated Preference Data (2024.naacl-long)
Copied to clipboard
| Challenge: | annotating preference data by humans is resource-intensive and creativity-demanding . existing methods face limitations in data diversity and quality . |
| Approach: | They propose a pipeline for annotating large-scale preference data without human annotators. |
| Outcome: | The proposed pipeline outperforms models fine-tuned on human-annotated safety preference data while maintaining a competitive edge in downstream tasks. |
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. |
AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails (2025.naacl-long)
Copied to clipboard
Shaona Ghosh, Prasoon Varshney, Makesh Narsimhan Sreedhar, Aishwarya Padmakumar, Traian Rebedea, Jibin Rajan Varghese, Christopher Parisien
| Challenge: | Existing safety-related content safety models are not well-suited for commercial use. |
| Approach: | They propose a taxonomy that can be used to categorize safety risks . it combines human annotations with a multi-LLM "jury" system to assess safety . they plan to open-source Aegis2.0 data and models to aid in safety guardrailing . |
| Outcome: | The proposed taxonomy can be used to assess the safety of human-LLM interactions . it can be trained on large, non-commercial datasets and is open-source . |
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. |
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. |