Word Alignment as Preference for Machine Translation

TL;DR

This paper introduces a novel method to improve machine translation by guiding large language models with word alignment preferences, effectively reducing hallucination and omission issues, and providing new evaluation strategies.

Contribution

It proposes using word alignment as a preference signal for optimizing LLM-based MT models and introduces GPT-4-based evaluation for hallucination and omission mitigation.

Findings

Word alignment preference optimization reduces hallucination and omission.

The method shows slight BLEU improvements and decreases in COMET scores.

GPT-4-based evaluation effectively assesses hallucination and omission mitigation.

Abstract

The problem of hallucination and omission, a long-standing problem in machine translation (MT), is more pronounced when a large language model (LLM) is used in MT because an LLM itself is susceptible to these phenomena. In this work, we mitigate the problem in an LLM-based MT model by guiding it to better word alignment. We first study the correlation between word alignment and the phenomena of hallucination and omission in MT. Then we propose to utilize word alignment as preference to optimize the LLM-based MT model. The preference data are constructed by selecting chosen and rejected translations from multiple MT tools. Subsequently, direct preference optimization is used to optimize the LLM-based model towards the preference signal. Given the absence of evaluators specifically designed for hallucination and omission in MT, we further propose selecting hard instances and utilizing GPT-4 to directly evaluate the performance of the models in mitigating these issues. We verify the rationality of these designed evaluation methods by experiments, followed by extensive results demonstrating the effectiveness of word alignment-based preference optimization to mitigate hallucination and omission. On the other hand, although it shows promise in mitigating hallucination and omission, the overall performance of MT in different language directions remains mixed, with slight increases in BLEU and decreases in COMET.