Search Results for author:
Found 2 papers, 1 papers with code
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots.
Applying Refusal-Vector Ablation to Llama 3.1 70B Agents
Our results imply that safety fine-tuning in chat models does not generalize well to agentic behavior, as we find that Llama 3. 1 Instruct models are willing to perform most harmful tasks without modifications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
