3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Language model agents increasingly automate post-training, but when given the full training stack they converge on supervised fine-tuning and spend most effort revising training data. Existing systems give the agent one kind of control, selecting rows from a fixed pool or calling a generator, whereas a human data engin...
During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking. Despite its risks to training efficiency and safety, monitoring and mitigating reward hacking d...
CHERRL is introduced, a Controllable Hacking Environment for Rubric-based RL that enables stable reproduction of reward hacking, explicit observation of reward divergence, and identification of hacking onset and analyzes different judge biases from the perspectives of discoverability and exploitability.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
