Entity · benchmark

NRC Generic Fundamentals Examination

benchmarkactiveprovisionalnrc-generic-fundamentals-examination-d796faf1·1 events·first seen 23h ago

Aliases: NRC Generic Fundamentals Examination

Co-occurring entities

U.S. Nuclear Regulatory Commission BM25 Google Retrieval-Augmented Fine-Tuning Gemma 4 Retrieval-Augmented Generation

More like this (12)

National Computer Rank Examination U.S. Nuclear Regulatory Commission ERC-8004 NERSC FMRP-LEAN EXAMS-V DSR Foundation Model RMISC NC-FFN GR2 Technical Report ARC Evals Agents' Last Exam

Recent events (1)

4arXiv · cs.CL·23h ago·source ↗

Gemma 4 31B benchmarked on NRC Reactor Operator Licensing Exam via fine-tuning and RAG configurations

Researchers benchmark eight fine-tuning and retrieval configurations of Gemma 4 31B-IT against the U.S. NRC Reactor Operator licensing examination across 14 Generic Fundamentals Examinations from 2015–2021. The best configuration—supervised fine-tuning with Gemini-distilled chain-of-thought rationales combined with fixed-size chunking RAG—passed 8 of 14 exams and reached 79.7% aggregate accuracy, near the 80% human passing threshold. Key findings include that no configuration without fine-tuning passed any exam, that preferred chunking strategy reverses depending on training state, and that RAFT underperforms standard SFT in matched retrieval environments.

Evaluation and Benchmarking Enterprise Deployment Patterns U.S. Nuclear Regulatory Commission BM25 Google +4 more