Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kumar, Somnath, Balloli, Vaibhav, Ranjit, Mercy, Ahuja, Kabir, Sitaram, Sunayana, Bali, Kalika, Ganu, Tanuja, Nambi, Akshay
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912178728075264
author Kumar, Somnath
Balloli, Vaibhav
Ranjit, Mercy
Ahuja, Kabir
Sitaram, Sunayana
Bali, Kalika
Ganu, Tanuja
Nambi, Akshay
author_facet Kumar, Somnath
Balloli, Vaibhav
Ranjit, Mercy
Ahuja, Kabir
Sitaram, Sunayana
Bali, Kalika
Ganu, Tanuja
Nambi, Akshay
contents Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive fine-tuning. We introduce a novel dynamic learning approach that optimizes prompt strategy, embedding model, and LLM per query at runtime. By adapting configurations dynamically, our method achieves significant improvements over static, best and random baselines. It operates efficiently in both offline and online settings, generalizing seamlessly across new languages and datasets. Leveraging Retrieval-Augmented Generation (RAG) with state-of-the-art multilingual embeddings, we achieve superior task performance across diverse linguistic contexts. Through systematic investigation and evaluation across 18 diverse languages using popular question-answering (QA) datasets we show our approach results in 10-15% improvements in multilingual performance over pre-trained models and 4x gains compared to fine-tuned, language-specific models.
format Preprint
id arxiv_https___arxiv_org_abs_2305_17740
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs
Kumar, Somnath
Balloli, Vaibhav
Ranjit, Mercy
Ahuja, Kabir
Sitaram, Sunayana
Bali, Kalika
Ganu, Tanuja
Nambi, Akshay
Computation and Language
Artificial Intelligence
Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive fine-tuning. We introduce a novel dynamic learning approach that optimizes prompt strategy, embedding model, and LLM per query at runtime. By adapting configurations dynamically, our method achieves significant improvements over static, best and random baselines. It operates efficiently in both offline and online settings, generalizing seamlessly across new languages and datasets. Leveraging Retrieval-Augmented Generation (RAG) with state-of-the-art multilingual embeddings, we achieve superior task performance across diverse linguistic contexts. Through systematic investigation and evaluation across 18 diverse languages using popular question-answering (QA) datasets we show our approach results in 10-15% improvements in multilingual performance over pre-trained models and 4x gains compared to fine-tuned, language-specific models.
title Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2305.17740