Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub

arXiv:2506.00482 · cs.LG, cs.AI, cs.CL · Submitted 2025-05-31 · Read on arXiv

cs.LG, cs.AI, cs.CL

Submitted: 2025-05-31

Updated: 2026-10-12

Code: https://github.com/rladmstn1714/BenchHub

Project page: https://axolotl-ai-cloud.github.io/axolotl

Terminology

• Benchmark — 6× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• CaLMQA: Exploring culturally specific long-form question answering across 23 languages
• Program Synthesis with Large Language Models
• Evaluating Large Language Models Trained on Code
• CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
• The Llama 3 Herd of Models
• NativQA: Multilingual Culturally-Aligned Natural Query for LLMs
• Liger Kernel: Efficient Triton Kernels for LLM Training
• MoralBench: Moral Evaluation of LLMs
• Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap
• KorMedMCQA: Multi-Choice Question Answering Benchmark for Korean Healthcare Professional Licensing Examinations
• LegalAgentBench: Evaluating LLM Agents in Legal Domain
• Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering
• Survey of Cultural Awareness in Language Models: Text and Beyond
• YourBench: Easy Custom Evaluation Sets for Everyone
• Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation
• Beyond Classification: Financial Reasoning in State-of-the-Art Language 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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks