Aligning Translation-Specific Understanding to General Understanding in Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910657525317632 |
|---|---|
| author | Huang, Yichong Li, Baohang Feng, Xiaocheng Fu, Chengpeng Huo, Wenshuai Liu, Ting Qin, Bing |
| author_facet | Huang, Yichong Li, Baohang Feng, Xiaocheng Fu, Chengpeng Huo, Wenshuai Liu, Ting Qin, Bing |
| contents | Large Language models (LLMs) have exhibited remarkable abilities in understanding complex texts, offering a promising path towards human-like translation performance. However, this study reveals the misalignment between the translation-specific understanding and the general understanding inside LLMs. This understanding misalignment leads to LLMs mistakenly or literally translating some complicated concepts that they accurately comprehend in the general scenarios (e.g., QA). To align the translation-specific understanding to the general one, we propose a novel translation process, DUAT (Difficult words Understanding Aligned Translation), explicitly incorporating the general understanding on the complicated content incurring inconsistent understanding to guide the translation. Specifically, DUAT performs cross-lingual interpretation for the difficult-to-translate words and enhances the translation with the generated interpretations. Furthermore, we reframe the external tools to improve DUAT in detecting difficult words and generating helpful interpretations. We conduct experiments on the self-constructed benchmark Challenge-WMT, consisting of samples that are prone to mistranslation. Human evaluation results on high-resource and low-resource language pairs indicate that DUAT significantly facilitates the understanding alignment, which improves the translation quality (up to +3.85 COMET) and reduces the literality of the translation by -25% to -51%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05072 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Aligning Translation-Specific Understanding to General Understanding in Large Language Models Huang, Yichong Li, Baohang Feng, Xiaocheng Fu, Chengpeng Huo, Wenshuai Liu, Ting Qin, Bing Computation and Language Large Language models (LLMs) have exhibited remarkable abilities in understanding complex texts, offering a promising path towards human-like translation performance. However, this study reveals the misalignment between the translation-specific understanding and the general understanding inside LLMs. This understanding misalignment leads to LLMs mistakenly or literally translating some complicated concepts that they accurately comprehend in the general scenarios (e.g., QA). To align the translation-specific understanding to the general one, we propose a novel translation process, DUAT (Difficult words Understanding Aligned Translation), explicitly incorporating the general understanding on the complicated content incurring inconsistent understanding to guide the translation. Specifically, DUAT performs cross-lingual interpretation for the difficult-to-translate words and enhances the translation with the generated interpretations. Furthermore, we reframe the external tools to improve DUAT in detecting difficult words and generating helpful interpretations. We conduct experiments on the self-constructed benchmark Challenge-WMT, consisting of samples that are prone to mistranslation. Human evaluation results on high-resource and low-resource language pairs indicate that DUAT significantly facilitates the understanding alignment, which improves the translation quality (up to +3.85 COMET) and reduces the literality of the translation by -25% to -51%. |
| title | Aligning Translation-Specific Understanding to General Understanding in Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.05072 |