Cost-Aware Best-LLM Identification using Dueling Feedback

arXiv:2609.30360 · cs.LG, cs.AI, stat.ML · Submitted 2026-09-24 · Read on arXiv

cs.LG, cs.AI, stat.ML

Submitted: 2026-09-24

Updated: 2026-09-24

Terminology

• Strong Stochastic Transitivity — 11× in this paper
• Low Noise Model — 10× in this paper
• Verification — 9× in this paper · explained in 2 episodes
• Moderate Stochastic Transitivity — 8× in this paper
• Pairwise Comparisons — 7× in this paper · explained in 2 episodes
• Total Ordering — 6× in this paper
• Weak Stochastic Transitivity — 6× in this paper
• Stochastic Triangle Inequality — 5× in this paper
• Adaptation — 4× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Dual Phase Cost Aware — 3× in this paper
• Accuracy — 2× in this paper · explained in 1 episode
• Adaptive Sampling — 2× in this paper · explained in 1 episode
• Adaptive sampling strategy — 2× in this paper · explained in 1 episode
• Generalized Likelihood Ratio Test — 2× in this paper
• Abstraction — 1× in this paper · explained in 1 episode
• Cost-Aware Round-Reject — 1× in this paper
• Dueling Bandit Cost-Aware Track and Stop — 1× in this paper
• General Identifiability Assumption — 1× in this paper
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
• LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks
• Line Goes Up? Inherent Limitations of Benchmarks for Evaluating Large Language Models
• Cost Aware Best Arm Identification
• Best-Arm Identification in Unimodal Bandits
• GenAI Arena: An Open Evaluation Platform for Generative Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks