paper-with-me

홈 › Papers

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages

2024-02-19 · Yuanchi Zhang, Yile Wang, Zijun Liu, Shuo Wang, Xiaolong Wang, Peng Li, Maosong Sun, Yang Liu

While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages. One common approach to mitigate this issue is to translate training data from resource-rich languages into other languages and then continue training. However, using the data obtained solely relying on translation while ignoring the original capabilities of LLMs across languages is not always effective, which we show will limit the performance of cross-lingual knowledge transfer. In this work, we propose SDRRL, a method based on Self-Distillation from Resource-Rich Languages that effectively improve multilingual performance by leveraging the internal capabilities of LLMs on resource-rich languages. We evaluate on different LLMs (LLaMA-2 and SeaLLM) and source languages across various comprehension and generation tasks, experimental results demonstrate that SDRRL can significantly enhance multilingual capabilities while minimizing the impact on original performance in resource-rich languages.

📄 PDF Abstract BibTeX arXiv:2402.12204

Code (1)

hiyouga/llama-factory 공식 구현 pytorch

Tasks

Transfer Learning

Similar Papers 제목 키워드 기반

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment

2024-11-25 · Shaolei Zhang, Kehao Zhang, Qingkai Fang, Shoutao Guo 외

Large language models (LLMs), with their powerful generative capabilities and vast knowledge, empower various tasks in everyday life. However, these abilities are primarily concentrated in high-resource languages, leavin…

Language ModelingLanguage ModellingLarge Language ModelTransfer Learning

How do Large Language Models Handle Multilingualism?

2024-02-29 · Yiran Zhao, Wenxuan Zhang, Guizhen Chen, Kenji Kawaguchi 외

Large language models (LLMs) have demonstrated impressive capabilities across diverse languages. This study explores how LLMs handle multilingualism. Based on observed language ratio shifts among layers and the relations…

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Tasks

2024-12-17 · Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang 외

Large language models (LLMs) have demonstrated impressive multilingual understanding and reasoning capabilities, driven by extensive pre-training multilingual corpora and fine-tuning instruction data. However, a performa…

Math

M-Prometheus: A Suite of Open Multilingual LLM Judges

2025-04-07 · José Pombal, Dongkeun Yoon, Patrick Fernandes, Ian Wu 외

The use of language models for automatically evaluating long-form text (LLM-as-a-judge) is becoming increasingly common, yet most LLM judges are optimized exclusively for English, with strategies for enhancing their mult…

Machine TranslationModel Selection

PolyPrompt: Automating Knowledge Extraction from Multilingual Language Models with Dynamic Prompt Generation

2025-02-27 · Nathan Roll

Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a…

MMLU