Fengrui Tian
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1Crypto×1ML×1
Frequent co-authors
Research Timeline
2026
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
The paper introduces REALISTA, a novel latent-space adversarial attack framework that generates semantically realistic and coherent prompts to effectively induce hallucinations in large language models (LLMs), outperforming existing methods.
Highlighted terms show continued research focus across papers
Papers
cs.CLcs.AIcs.CRRecentMay 12, 2026
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
Buyun Liang, Jinqi Luo, Liangzu Peng, Kwan Ho Ryan Chan +5 more
The paper introduces REALISTA, a novel latent-space adversarial attack framework that generates semantically realistic and coherent prompts to effectively induce hallucinations in large language model…
View →