Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation
cs.LG, math.OC, stat.ML
Submitted: 2026-08-30
Updated: 2026-08-30
Code: https://github.com/HamedKhosravi99/logged-llm-comparison-audit
Terminology
Sources
- Measuring what Matters: Construct Validity in Large Language Model Benchmarks
- Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data
- Causal methods for LLM development and evaluation
- Budgeted Active Experimentation for Treatment Effect Estimation from Observational and Randomized Data
- A Survey on LLM-as-a-Judge
- RouterBench: A Benchmark for Multi-LLM Routing System
- LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing
- SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
- Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge
- HelpSteer2: Open-source dataset for training top-performing reward models
- Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing
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