| WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models | Jun 26, 2024 | ChatbotRed Teaming | CodeCode Available | 2 |
| The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm | Jun 26, 2024 | Cross-Lingual TransferRed Teaming | —Unverified | 0 |
| CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference | Jun 25, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
| Leveraging Reinforcement Learning in Red Teaming for Advanced Ransomware Attack Simulations | Jun 25, 2024 | Red TeamingReinforcement Learning (RL) | —Unverified | 0 |
| Steering Without Side Effects: Improving Post-Deployment Control of Language Models | Jun 21, 2024 | Red TeamingTruthfulQA | CodeCode Available | 0 |
| Adversaries Can Misuse Combinations of Safe Models | Jun 20, 2024 | Red Teaming | —Unverified | 0 |
| Jailbreaking as a Reward Misspecification Problem | Jun 20, 2024 | Red Teaming | CodeCode Available | 1 |
| Finding Safety Neurons in Large Language Models | Jun 20, 2024 | MisinformationRed Teaming | —Unverified | 0 |
| Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding | Jun 17, 2024 | 16kLanguage Modelling | CodeCode Available | 0 |
| Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner | Jun 17, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 1 |
