Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation

arXiv:2409.00696 · cs.CL, cs.AI · Submitted 2024-09-01 · Read on arXiv

cs.CL, cs.AI

Submitted: 2024-09-01

Updated: 2026-10-12

Code: https://github.com/eth-sri/polyrating

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• Gemini: A Family of Highly Capable Multimodal Models
• Humans or LLMs as the Judge? A Study on Judgement Biases
• Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
• Evading Data Contamination Detection for Language Models is (too) Easy
• Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
• Are We Done with MMLU?
• Human Feedback is not Gold Standard
• Holistic Evaluation of Language Models
• WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
• MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures
• GPT-4 Technical Report
• Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
• A Long Way to Go: Investigating Length Correlations in RLHF
• How I won the "Chess Ratings - Elo vs the Rest of the World" Competition
• Large Language Models are not Fair Evaluators
• Style Over Substance: Evaluation Biases for Large Language Models
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

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