Firehose

15 SEP 2026 · Paper

ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals

This paper tests the robustness of rubrics generated by language models as reward signals in reinforcement learning, finding that even generic rubrics can be exploited 64% of the time, while tailored rubrics can be used to create fake answers. Practitioners should care because this can lead to biased grading and evaluation.

language models rubric-based reinforcement learning adversarial examples evaluation benchmarks

Browse by tag

ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals