paper-with-me

Papers

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

2024-06-23 · Lynn Chua, Badih Ghazi, Yangsibo Huang, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chulin Xie, Chiyuan Zhang

Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, effectively being crosslingual? This study evaluates six state-of-the-art LLMs on inherently crosslingual tasks. We observe that while these models show promising surface-level crosslingual abilities on machine translation and embedding space analyses, they struggle with deeper crosslingual knowledge transfer, revealing a crosslingual knowledge barrier in both general (MMLU benchmark) and domain-specific (Harry Potter quiz) contexts. We observe that simple inference-time mitigation methods offer only limited improvement. On the other hand, we propose fine-tuning of LLMs on mixed-language data, which effectively reduces these gaps, even when using out-of-domain datasets like WikiText. Our findings suggest the need for explicit optimization to unlock the full crosslingual potential of LLMs. Our code is publicly available at https://github.com/google-research/crosslingual-knowledge-barriers.

📄 PDF Abstract BibTeX arXiv:2406.16135

Code (1)

google-research/crosslingual-knowledge-barriers 공식 구현 pytorch

Tasks

Machine TranslationMMLUTransfer Learning

Similar Papers 제목 키워드 기반

Tracing Multilingual Factual Knowledge Acquisition in Pretraining

2025-05-20 · Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Felicia Körner 외

Large Language Models (LLMs) are capable of recalling multilingual factual knowledge present in their pretraining data. However, most studies evaluate only the final model, leaving the development of factual recall and c…

An Empirical Study on Crosslingual Transfer in Probabilistic Topic Models

2018-10-13 · CL 2020 3 · Shudong Hao, Michael J. Paul

Probabilistic topic modeling is a popular choice as the first step of crosslingual tasks to enable knowledge transfer and extract multilingual features. While many multilingual topic models have been developed, their ass…

Topic ModelsTransfer Learning

Monitio - Large Scale MT for Multilingual Media Monitoring

2022-06-01 · EAMT 2022 6 · Carlos Amaral, Sebastião Miranda

Monitio is a real-time crosslingual global media monitoring platform which delivers actionable insights beyond human scale and capabilities. Our system continuously ingests a massive number of multilingual data sources t…

Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models

2023-11-15 · James A. Michaelov, Catherine Arnett, Tyler A. Chang, Benjamin K. Bergen

Abstract grammatical knowledge - of parts of speech and grammatical patterns - is key to the capacity for linguistic generalization in humans. But how abstract is grammatical knowledge in large language models? In the hu…

Sentence

NeoBabel: A Multilingual Open Tower for Visual Generation

2025-07-08 · Mohammad Mahdi Derakhshani, Dheeraj Varghese, Marzieh Fadaee, Cees G. M. Snoek

Text-to-image generation advancements have been predominantly English-centric, creating barriers for non-English speakers and perpetuating digital inequities. While existing systems rely on translation pipelines, these i…

Image GenerationText to Image GenerationText-to-Image Generation