LLM-RBMT
What it is
LLM-RBMT is a framework for building machine translators for extremely low-resource languages. It has mostly been applied to Owens Valley Paiute (OVP), a critically endangered Indigenous language of California with fewer than ten fluent speakers. The system translates English into OVP, but the way it does so is the point of this example.
Under the LLM-RBMT paradigm, language models never freely generate the target language. Instead, the model's job is to read an English sentence and fill in a structured form: a set of grammar "slots" (subject, verb, object, tense, number, and so on) defined by community-curated rules. A separate, deterministic program then renders that filled-in form into the actual OVP sentence. The model handles the messy English-understanding part while the hand-built grammar makes sure the sentence is grammatical.
Early versions relied on large proprietary models for this step, but recent work has shown the same approach works with small, open-weight models. This is important because it can help address concerns around environmental impact and data sovereignty.
Upsides
- Careful about what data it uses. The research uses AI in many ways to compare different approaches. Authors are careful to use only public, non-culturally-sensitive material: basic vocabulary and grammar. No sentences elicited from speakers or anything drawn from stories or private archives are used.
- Aimed at sovereignty-respecting systems by design. The goal of the project is to move toward translation systems that take data sovereignty and environmental impact seriously from the start.
Downsides
- Helping users interpret the output is an open problem. Making sure users understand what the outputs are, and aren't, before they rely on them is its own task that the project has not yet solved.
- The limits of the approach aren't yet clear. How well it actually serves learners, what it does to or for the pedagogy, and where the method breaks down are open questions.