6 citations · 14 across the 11 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Debate Training Reduces Reward Hacking in RLAIF
Zachary Kenton, Lili Janzer, Rory Greig +8
We demonstrate that RL finetuning an LLM using debate, a two-player adversarial game between a generator and a critic adjudicated by a weaker LLM judge, reduces reward hacking comp…
cs.LG2024★ 6 cited
On scalable oversight with weak LLMs judging strong LLMs
Zachary Kenton, Noah Y. Siegel, János Kramár +8
Scalable oversight protocols aim to enable humans to accurately supervise superhuman AI. In this paper we study debate, where two AI's compete to convince a judge; consultancy, whe…
cs.LG2023
Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions
Ezgi Korkmaz, Jonah Brown-Cohen
Learning in MDPs with highly complex state representations is currently possible due to multiple advancements in reinforcement learning algorithm design. However, this incline in c…