works on
actor-critic PPO 1confidence estimation 1large language models 1quantitative prediction 1reinforcement learning 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.HCShow all

1 paper · 1 filter

cs.HC2025

Learning to Lie: Reinforcement Learning Attacks Damage Human-AI Teams and Teams of LLMs

Abed Kareem Musaffar, Anand Gokhale, Sirui Zeng +4

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversari…