REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations 事件

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations arXiv:2605.12813v2 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs. We formulate hallucination elicitation as a constrained optimization problem, where the goal is to find semantically coherent adversarial prompts that ar