# Typologically-Informed Candidate Reranking for LLM-based Translation into Low-Resource Languages

arXiv: https://arxiv.org/abs/2602.01162 · HTML: https://mlsanity.com/paper/2602.01162/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 1 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons](https://mlsanity.com/paper/2404.02431/) (2024)
- [Why do language models perform worse for morphologically complex languages?](https://mlsanity.com/paper/2411.14198/) (2024)
- [Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages](https://mlsanity.com/paper/2501.06346/) (2025)
- [Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations](https://mlsanity.com/paper/2004.14923/) (2020)
- [Creative Beam Search: LLM-as-a-Judge For Improving Response Generation](https://mlsanity.com/paper/2405.00099/) (2024)
- [Improving Low-Resource Machine Translation via Cross-Linguistic Transfer from Typologically Similar High-Resource Languages](https://mlsanity.com/paper/2501.00045/) (2024)

## Abstract (arXiv)

Large language models trained predominantly on high-resource languages exhibit systematic biases toward dominant typological patterns, leading to structural non-conformance when translating into typologically divergent low-resource languages. We present a framework that leverages linguistic typology to improve translation quality without parallel training data or model retraining. The framework consists of two components: the Universal Metalinguistic Framework (UMF), which represents languages as structured profiles across 16 typological dimensions with divergence-weighted scoring, and the Computational Engine, which operates through linguistic disambiguation during generation and typological compliance scoring during selection. Evaluation across nine language pairs demonstrates intervention rates strongly correlating with typological distance from English. In experiments on 341 English sentences each having different morphological and syntactic phenomena, the framework shows an intervention precision of 48.16% for conservatively treated languages, 28.15% for morphologically dense languages, and 86.26% for structurally profiled languages. The framework requires no parallel training data and operates with any LLM capable of producing multiple candidate outputs, enabling practical deployment for under-resourced languages.