Contrastive Preference Optimization: Pushing The Boundaries Of LLM Performance In Machine Translation | Awesome LLM Papers Contribute to Awesome LLM Papers

Awesome LLM Papers

A curated collection of research papers on Large Language Models (LLMs), transformers, prompting, fine-tuning, and multi-modal systems. Maintained by Sean Moran.

Contact Sean Moran about this survey or website. Made with Jekyll and Hyde.

Contrastive Preference Optimization: Pushing The Boundaries Of LLM Performance In Machine Translation

Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin van Durme, Kenton Murray, Young Jin Kim . No Venue 2024

[Paper] [Paper]   Search on Google Scholar   Search on Semantic Scholar
Datasets Efficiency Fine Tuning Model Architecture

Moderate-sized large language models (LLMs) – those with 7B or 13B parameters – exhibit promising machine translation (MT) performance. However, even the top-performing 13B LLM-based translation models, like ALMA, does not match the performance of state-of-the-art conventional encoder-decoder translation models or larger-scale LLMs such as GPT-4. In this study, we bridge this performance gap. We first assess the shortcomings of supervised fine-tuning for LLMs in the MT task, emphasizing the quality issues present in the reference data, despite being human-generated. Then, in contrast to SFT which mimics reference translations, we introduce Contrastive Preference Optimization (CPO), a novel approach that trains models to avoid generating adequate but not perfect translations. Applying CPO to ALMA models with only 22K parallel sentences and 12M parameters yields significant improvements. The resulting model, called ALMA-R, can match or exceed the performance of the WMT competition winners and GPT-4 on WMT’21, WMT’22 and WMT’23 test datasets.

https://huggingface.co/discussions/paper/65a776634908b2676c709a74

Similar Work