arXiv Computation and Language By Bin Zhu, Yi Xie, Yanghui Rao

Stopping and Routing LLM Judge Panels

Read the original on arXiv Computation and Language →

arXiv:2608. 19802v1 Announce Type: new Abstract: LLM evaluation pipelines often have many candidate judges: general LLM-as-a-judge prompts, reward models, safety classifiers, confidence variants, and task-specific verifiers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
2d ago

Share the Judge, Learn the Deferral: Where Specialization Helps LLM Evaluation

The paper investigates two strategies for improving large language model (LLM) evaluation: specialized judge weights and rule‑based deferral policies. Experiments on nearly 100,000 rubric‑conditioned samples show that correct rubrics boost accuracy, while incorrect ones hurt it, and that splitting training data into criterion‑specific experts can severely degrade performance unless the experts are warm‑started from a unified model. The authors demonstrate that lightweight deferral cascades can match or exceed the accuracy of larger standalone judges at a fraction of the compute cost, and they provide practical design rules for building efficient, reliable LLM evaluators.

By Ye Chen, Weining Zhang