SAGE: A Generic Framework for LLM Safety Evaluation
Open Access
- 1 January 2025
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 11-33
Abstract
Madhur Jindal, Hari Shrawgi, Parag Agrawal, Sandipan Dandapat. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2025.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- The Big Five and divergent thinking: A meta-analysisPersonality and Individual Differences, 2023
- Large language models encode clinical knowledgeNature, 2023
- Unveiling the Implicit Toxicity in Large Language Models2023
- AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications2023
- Red Teaming Language Models with Language Models2022
- TruthfulQA: Measuring How Models Mimic Human Falsehoods2022
- BBQ: A hand-built bias benchmark for question answering2022
- On the Dangers of Stochastic Parrots2021
- HateCheck: Functional Tests for Hate Speech Detection Models2021
- RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models2020