13 citations · 14 across the 14 of their papers we have counts for
7 papers · 1 filter
Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
Thanawat Lodkaew, Johannes Ackermann, Soichiro Nishimori +3
A growing failure mode in agent evaluation and training is that models can achieve high evaluation scores by exploiting shortcuts instead of solving the intended task, producing de…
Mitigating Reward Hacking in RLHF via Advantage Sign Robustness
Shinnosuke Ono, Johannes Ackermann, Soichiro Nishimori +2
Reward models (RMs) used in reinforcement learning from human feedback (RLHF) are vulnerable to reward hacking: as the policy maximizes a learned proxy reward, true quality plateau…
Towards Scalable Oversight via Partitioned Human Supervision
Ren Yin, Takashi Ishida, Masashi Sugiyama
As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and tra…
LLM Routing with Dueling Feedback
Chao-Kai Chiang, Takashi Ishida, Masashi Sugiyama
We study LLM routing, the problem of selecting the best model for each query while balancing user satisfaction, model expertise, and inference cost. We formulate routing as context…
Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback
Johannes Ackermann, Takashi Ishida, Masashi Sugiyama
Reinforcement Learning from Human Feedback (RLHF) allows us to train models, such as language models (LMs), to follow complex human preferences. In RLHF for LMs, we first train an…
LocalDrop: A Hybrid Regularization for Deep Neural Networks
Ziqing Lu, Chang Xu, Bo Du +3
In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas. We propose a new approach for the regularization of neural networks…