Does System One Transfer? Calibrated Typed-Decision Models, Label Budgets, and Translation for Indonesian Regional Languages

cs.CL, cs.LG

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: 14 pages, 5 figures, 8 tables. Pre-registered study; code, pre-registration and all predictions: https://github.com/tnromy/evaluating-system-one-models-for-indonesian-regional-languages

Code: https://github.com/tnromy/evaluating-system-one-models-for-indonesian-regional-languages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Evaluating Decision Models for Text Annotation in Computational Social Science
• Evaluating and Benchmarking the System One Model Jev
• mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
• Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name, Not the Definition Bound to It
• Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification
• Language Models (Mostly) Know What They Know
• JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering