Decision Models vs. LLMs as Rubric Judges: Cheaper, Faster, and Wrong in the Same Places

arXiv:2609.29769 · cs.CL · Submitted 2026-09-24 · Read on arXiv

cs.CL

Submitted: 2026-09-24

Updated: 2026-10-13

Comments: 58 pages, 11 figures, 37 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 128× in this paper · explained in 1 episode
• LLM judge — 117× in this paper · explained in 2 episodes
• Abstention — 21× in this paper · explained in 1 episode
• Benchmark — 18× in this paper · explained in 2 episodes
• Calibration — 8× in this paper · explained in 7 episodes
• Provenance — 7× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Deferral — 3× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 3× in this paper · explained in 3 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Generative AI — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Intelligence Advanced Research Projects Activity — 1× in this paper
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• HealthBench: Evaluating Large Language Models Towards Improved Human Health
• TransGAT: Transformer-Based Graph Neural Networks for Multi-Dimensional Automated Essay Scoring
• Are Large Language Models Good Essay Graders?
• Language Models (Mostly) Know What They Know
• Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Tasks
• Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering