SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
🚀
3
Eliciting LLM Hallucinations
Kwan Ho Ryan Chan
ryanckh
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
29 days ago
Conformal Information Pursuit for Interactively Guiding Large Language
Models
liked
a Space
29 days ago
byliang/SECA
authored
a paper
9 months ago
Unsupervised Manifold Linearizing and Clustering
Organizations
None yet
liked
a
Space
29 days ago