Cite
Notes
Only stored in your browser.
Attribution
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
arXiv 2026
LLM Safety From Within: Detecting Harmful Content with Internal Representations
SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
arXiv 2025
from 3 papers
Ashton Anderson
Zhenwei Tang
Blair Yang
Haolun Wu
Linfeng Du
Qianfeng Wen
Ye Yuan
Yilun Liu