paper-with-me

Papers

Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages

2024-01-11 · Zhuoyuan Mao, Yen Yu

This article introduces contrastive alignment instructions (AlignInstruct) to address two challenges in machine translation (MT) on large language models (LLMs). One is the expansion of supported languages to previously unseen ones. The second relates to the lack of data in low-resource languages. Model fine-tuning through MT instructions (MTInstruct) is a straightforward approach to the first challenge. However, MTInstruct is limited by weak cross-lingual signals inherent in the second challenge. AlignInstruct emphasizes cross-lingual supervision via a cross-lingual discriminator built using statistical word alignments. Our results based on fine-tuning the BLOOMZ models (1b1, 3b, and 7b1) in up to 24 unseen languages showed that: (1) LLMs can effectively translate unseen languages using MTInstruct; (2) AlignInstruct led to consistent improvements in translation quality across 48 translation directions involving English; (3) Discriminator-based instructions outperformed their generative counterparts as cross-lingual instructions; (4) AlignInstruct improved performance in 30 zero-shot directions.

📄 PDF Abstract BibTeX arXiv:2401.05811

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

BLOOMZ BLOOMZ is a Multitask prompted finetuning (MTF) variant of BLOOM.

Similar Papers 제목 키워드 기반

Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning

2025-09-01 · Yu Liu, Yanan Cao, Xixun Lin, Yanmin Shang 외 arxiv

Knowledge graph completion (KGC) aims to infer new knowledge and make predictions from knowledge graphs. Recently, large language models (LLMs) have exhibited remarkable reasoning capabilities. LLM-enhanced KGC methods p…

Knowledge Graph CompletionContrastive LearningKnowledge GraphsLink Prediction

Contrastive Instruction Tuning

2024-02-17 · Tianyi Lorena Yan, Fei Wang, James Y. Huang, Wenxuan Zhou 외

Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks. However, current LLMs exhibit limited robustness to unseen instructions, generating inc…

Sentence

Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)

2025-05-26 · Subba Reddy Oota, Akshett Jindal, Ishani Mondal, Khushbu Pahwa 외

Transformer-based language models, though not explicitly trained to mimic brain recordings, have demonstrated surprising alignment with brain activity. Progress in these models-through increased size, instruction-tuning,…

Image Captioning

CodecLM: Aligning Language Models with Tailored Synthetic Data

2024-04-08 · Zifeng Wang, Chun-Liang Li, Vincent Perot, Long T. Le 외

Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. …

Instruction Following

Evolutionary Contrastive Distillation for Language Model Alignment

2024-10-10 · Julian Katz-Samuels, Zheng Li, Hyokun Yun, Priyanka Nigam 외

The ability of large language models (LLMs) to execute complex instructions is essential for their real-world applications. However, several recent studies indicate that LLMs struggle with challenging instructions. In th…

Contrastive LearningInstruction FollowingLanguage ModelingLanguage Modelling+1