Nsanku benchmark shows current LLMs achieve only modest zero-shot translation scores on 43 Ghanaian languages, with no model reaching both high average performance and high cross-language consistency.
Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis , booktitle =
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
ReflectMT internalizes reflection via two-stage RL to enable direct high-quality machine translation that outperforms explicit reasoning models like DeepSeek-R1 on WMT24 while using 94% fewer tokens.
SLoW selects low-frequency word dictionaries to boost LLM translation quality and efficiency across 100 languages from FLORES.
DIP interleaves English word translations into non-English prompts to boost multilingual reasoning on synthetic benchmarks spanning 10-200 languages.
BM25 retrieval makes many-shot ICL for low-resource MT roughly 5x more data-efficient, with 50 examples matching 250 random ones and 250 matching 1000.
Frequent sentence-level text improves LLM prompting and fine-tuning performance across math, translation, commonsense, and tool-use tasks via a proposed frequency law and curriculum ordering.
SLR on user modeling in MDE finds disconnected proposals emphasizing static easy traits, limited dynamic evolution and tools, and calls for unified models plus ML-driven personalization pipelines.
citing papers explorer
-
Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages
Nsanku benchmark shows current LLMs achieve only modest zero-shot translation scores on 43 Ghanaian languages, with no model reaching both high average performance and high cross-language consistency.
-
ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
ReflectMT internalizes reflection via two-stage RL to enable direct high-quality machine translation that outperforms explicit reasoning models like DeepSeek-R1 on WMT24 while using 94% fewer tokens.
-
SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models
SLoW selects low-frequency word dictionaries to boost LLM translation quality and efficiency across 100 languages from FLORES.
-
Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models
DIP interleaves English word translations into non-English prompts to boost multilingual reasoning on synthetic benchmarks spanning 10-200 languages.
-
An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages
BM25 retrieval makes many-shot ICL for low-resource MT roughly 5x more data-efficient, with 50 examples matching 250 random ones and 250 matching 1000.
-
Adam's Law: Textual Frequency Law on Large Language Models
Frequent sentence-level text improves LLM prompting and fine-tuning performance across math, translation, commonsense, and tool-use tasks via a proposed frequency law and curriculum ordering.
-
A Low-Code Approach for the Automatic Personalization of Conversational Agents
SLR on user modeling in MDE finds disconnected proposals emphasizing static easy traits, limited dynamic evolution and tools, and calls for unified models plus ML-driven personalization pipelines.
- Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
- Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation