Chien-Sheng Wu, Caiming Xiong, Divyansh Agarwal, Fan Yin, Philippe Laban, Xiangyu Peng, Yilun Zhou, Yixin Mao, Vaibhav Vats, Linnea Ross, Harmbench… Wildguardtest
We lifted 3 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| argilla-io/argilla | canonical | 3 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| full_qualified_class_name | Ran | argilla-io/argilla/argilla-server/src/argilla_server/logging.py code served (permissive licence) · get_code("92ee2cd14509b1ec") |
| get_logger_for_class | Ran | argilla-io/argilla/argilla-server/src/argilla_server/logging.py code served (permissive licence) · get_code("991c771d8d16fb58") |
| remove_suffix | Ran | argilla-io/argilla/argilla-server/src/argilla_server/helpers.py code served (permissive licence) · get_code("506be8e0370a57fb") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Malicious content generated by large language models (LLMs) can pose varying degrees of harm. Although existing LLM-based moderators can detect harmful content, they struggle to assess risk levels and may miss lower-risk outputs. Accurate risk assessment allows platforms with different safety thresholds to tailor content filtering and rejection. In this paper, we introduce per-topic severity rubrics for 11 harmful topics and build BingoGuard, an LLM-based moderation system designed to predict both binary safety labels and severity levels. To address the lack of annotations on levels of severity, we propose a scalable generate-then-filter framework that first generates responses across different severity levels and then filters out lowquality responses. Using this framework, we create BingoGuardTrain, a training dataset with 54,897 examples covering a variety of topics, response severity, styles, and BingoGuardTest, a test set with 988 examples explicitly labeled based on our severity rubrics that enables fine-grained analysis on model behaviors on different severity levels. Our BingoGuard-8B, trained on BingoGuardTrain, achieves the state-of-the-art performance on several moderation benchmarks, including Wild-GuardTest and HarmBench, as well as BingoGuardTest, outperforming best public models, WildGuard, by 4.3%. Our analysis demonstrates that incorporating severity levels into training significantly enhances detection performance and enables the model to effectively gauge the severity of harmful responses. 1 Warning: this paper includes red-teaming examples that may be harmful in nature.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2503.06550")
get_code_for_paper("2503.06550")
have("2503.06550")
Connect an agent — have() is free.