Same Outputs, Different Scores: Auditing the Unchecked Graders of Multimodal LLM Benchmarks
cs.AI, cs.CL, cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/ahmadhasan2k8/grader-audit
Terminology
Sources
- Pixtral 12B
- Qwen2.5-VL Technical Report
- Qwen3-VL Technical Report
- Lessons from the Trenches on Reproducible Evaluation of Language Models
- Answer Matching Outperforms Multiple Choice for Language Model Evaluation
- Gemma 4 Technical Report
- The Llama 3 Herd of Models
- Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents