5 papers
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
Shaomu Tan, Dawei Zhu, Ke Tran +5
Iterative self-refinement is a simple inference-time strategy for machine translation: an LLM revises its own translation over multiple inference-time passes. Yet document-scale re…
XRAG: Cross-lingual Retrieval-Augmented Generation
Wei Liu, Sony Trenous, Leonardo F. R. Ribeiro +2
We propose XRAG, a novel benchmark designed to evaluate the generation abilities of LLMs in cross-lingual Retrieval-Augmented Generation (RAG) settings where the user language does…
A Preference-driven Paradigm for Enhanced Translation with Large Language Models
Dawei Zhu, Sony Trenous, Xiaoyu Shen +3
Recent research has shown that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) using only a small amount of paralle…
Trained MT Metrics Learn to Cope with Machine-translated References
Jannis Vamvas, Tobias Domhan, Sony Trenous +2
Neural metrics trained on human evaluations of MT tend to correlate well with human judgments, but their behavior is not fully understood. In this paper, we perform a controlled ex…
The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation
Tobias Domhan, Eva Hasler, Ke Tran +3
Vocabulary selection, or lexical shortlisting, is a well-known technique to improve latency of Neural Machine Translation models by constraining the set of allowed output words dur…