{"version":1,"type":"story","url":"https://digestai.news/story/researchers-test-typed-decision-models-on-indonesian-regional-language","json":"https://digestai.news/story/researchers-test-typed-decision-models-on-indonesian-regional-language.json","markdown":"https://digestai.news/story/researchers-test-typed-decision-models-on-indonesian-regional-language.md","slug":"researchers-test-typed-decision-models-on-indonesian-regional-language","headline":"Researchers test Typed-Decision models on Indonesian regional languages","summary":"A new study evaluates typed-decision models—fast, low-cost systems that return labels and probabilities in one step—on Indonesian regional languages. The paper, posted on arXiv, compares the commercial **Jev** model and the open-source **Laya-multilingual** model using two datasets: **NusaX sentiment** (12 languages) and **NusaTranslation sentiment and emotion** (7 languages).\n\nThe findings show **Jev** performs better on sentences closer to Indonesian but struggles with distant languages, where accuracy improves by up to **37.2 points** when given human Indonesian translations. While its calibration error remains stable, its ability to self-rank errors weakens. Retraining classifiers requires **more than 500 labels per language** to match **Jev**’s zero-shot performance in nine of ten **NusaX** languages. A hybrid approach—routing **Jev**’s least confident decisions (10–30%) to a local **IndoBERT** classifier—matches or exceeds the best system at **24–77% lower API cost** than routing to an LLM. Five other commercial LLMs (three **Claude** and three **GPT** models) outperform **Jev** by **4–14 points** but cost hundreds of times more.","keyPoints":["Typed-decision models like **Jev** and **Laya-multilingual** tested on 12+ Indonesian regional languages using **NusaX** and **NusaTranslation** datasets","**Jev**’s accuracy rises by up to **37.2 points** with Indonesian translations for distant languages, but self-error ranking degrades","A hybrid cascade (routing low-confidence outputs to **IndoBERT**) matches LLM performance at **24–77% lower cost**"],"whyItMatters":"Proves typed-decision models can generalize beyond English, offering a cheaper alternative for low-resource languages if calibrated with translations.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["Jev","Laya-multilingual","IndoBERT","Claude Haiku","Claude","GPT"],"people":[]},"firstPublishedAt":"2026-10-14T04:00:00Z","updatedAt":"2026-10-14T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.CL","title":"Does System One Transfer? Calibrated Typed-Decision Models, Label Budgets, and Translation for Indonesian Regional Languages","url":"https://arxiv.org/abs/2610.14112","publishedAt":"2026-10-14T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers test Typed-Decision models on Indonesian regional languages\", 14 October 2026, https://digestai.news/story/researchers-test-typed-decision-models-on-indonesian-regional-language","publisher":"Digest AI","title":"Researchers test Typed-Decision models on Indonesian regional languages","datePublished":"2026-10-14T04:00:00Z","url":"https://digestai.news/story/researchers-test-typed-decision-models-on-indonesian-regional-language"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}