Cite
Notes
Only stored in your browser.
Attribution
Agentic Reasoning for Large Language Models
arXiv 2026
Internal Activation as the Polar Star for Steering Unsafe LLM Behavior
arXiv 2025
Integrative Decoding: Improve Factuality via Implicit Self-consistency
arXiv 2024
A Survey on the Honesty of Large Language Models
from 4 papers
Cheng Qian
Heng Ji
professor
Cheng Yang
Chi Wang
Chufan Shi
Deng Cai
Denghui Zhang
Dongqi Fu
Duo Zhou
Gaotang Li