RT-LRM benchmark finds Large Reasoning Models more fragile than standard LLMs to risks like CoT-hijacking and prompt-induced issues.
12345.6789
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Derives expected L2 string stability conditions for human-led platoons under stochastic delays via integral inequalities in a stochastic hybrid system model.
citing papers explorer
-
Red Teaming Large Reasoning Models
RT-LRM benchmark finds Large Reasoning Models more fragile than standard LLMs to risks like CoT-hijacking and prompt-induced issues.
-
Expected String Stability of Human-Led Vehicle Platoons under Stochastic Communication Delays (Full Version)
Derives expected L2 string stability conditions for human-led platoons under stochastic delays via integral inequalities in a stochastic hybrid system model.