AI in Education
UK EN

Papers tagged with: #benchmarking

8.1
psychometric_modeling

One Percent of the Bank: Adaptive Item Selection Reads Targeted Contamination Up While the Whole Bank Barely Moves

Guan-Yuan Chen, Ya-Fen Yeh · Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.23156543 · gemini-3.1-flash-lite

Read full analysis →

8.0
assessment_design

Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks

Michael Kouremetis, Ads Dawson, Raja Sekhar Rao Dheekonda, Brian Greunke · arXiv (2026) · doi:10.48550/arxiv.2607.21763 · gemini-3.1-flash-lite

Read full analysis →

8.0
psychometric_modeling

Laplace-PSN-IRT: Uncertainty Quantification for Neural Item Response Theory Models of LLM Benchmarks

Juan Francisco, Mandujano Reyes · arXiv (2026) · doi:10.48550/arxiv.2607.25257 · gemini-3.1-flash-lite

Read full analysis →

7.5
psychometric_modeling

Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple-Choice Benchmarks

Xiao Fei, Yang Zhang, Sarah Almeida Carneiro, Michalis Vazirgiannis · arXiv (2026) · doi:10.48550/arxiv.2608.02966 · gemini-3.1-flash-lite

Read full analysis →

7.5
assessment_design

Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests

Thanawat Lodkaew, Johannes Ackermann, Soichiro Nishimori, Nontawat Charoenphakdee, Masashi Sugiyama, Takashi Ishida · arXiv (2026) · doi:10.48550/arxiv.2606.07379 · gemini-3.1-flash-lite

Read full analysis →

7.2
assessment_design

MS-Exam-Gen: Source-Grounded Benchmark Construction for Evaluating LLMs on Textual Multiple Sclerosis MRI Knowledge

Abdul Basit, Muhammad Abdullah Hanif, Muhammad Shafique · arXiv (2026) · doi:10.48550/arxiv.2610.06170 · gemini-3.1-flash-lite

Read full analysis →

7.3
psychometric_modeling

Auditing LLM Benchmarks with Item Response Theory

Sander Land, Daniel M. Bikel · arXiv (2026) · doi:10.48550/arxiv.2605.30504 · gemini-3.6-flash

Read full analysis →

7.3
psychometric_modeling

Which AI model is truly the best: how reliable are public benchmarks of frontier AI models?

Miloš Kankaraš · Zenodo (CERN European Organization for Nuclear Research) (2026) · doi:10.5281/zenodo.22998204 · gemini-3.7-flash

Read full analysis →

7.2
psychometric_modeling

Extending Item Response Theory for Efficient and Meaningful Multilingual Evaluation

Gili Lior, Tzviel Frostig, Gabriel Stanovsky, Matan Eyal · arXiv (2026) · doi:10.48550/arxiv.2606.15643 · gemini-3.7-flash

Read full analysis →