SPIN Unprocessed October 15, 2026 ai_technology research
Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena
View original on arxiv.orgOverview
arXiv:2610.19095v1 Announce Type: new Abstract: Chatbot Arena ranks language models with the Bradley-Terry model, which gives each model one score and so assumes Luce's choice axiom. Choice theory predicts where this fails: near-copies are told apart more decisively than their scores imply. On 1.8 million Arena votes, votes between versions of one model are 1.37 times as decisive as Bradley-Terry predicts, between sizes of one generation 1.26 times and between models of one lab 1.12 times; a rel
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from arXiv Computation and Language
View all →- Copy-Paste Language Models
- Do Syntax Heads Influence Model Behavior?
- Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules
- DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression
- Weighted Ensemble Sampling for Rare-Event Estimation in Language Models
- NEPSEE: A Double-Annotated Benchmark for Nepali Sentiment Analysis
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO