@inproceedings{tsvetkov-kipnis-2024-information,
    title = "Information Parity: Measuring and Predicting the Multilingual Capabilities of Language Models",
    author = "Tsvetkov, Alexander  and
      Kipnis, Alon",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.findings-emnlp.468/",
    doi = "10.18653/v1/2024.findings-emnlp.468",
    pages = "7971--7989",
    abstract = "Large Language Models (LLMs) are increasingly deployed in user-facing applications worldwide, necessitating handling multiple languages across various tasks. We propose a metric called Information Parity (IP) that can predict an LLM{'}s capabilities across multiple languages in a task-agnostic manner. IP is well-motivated from an information theoretic perspective: it is associated with the LLM{'}s efficiency of compressing the text in a given language compared to a reference language. We evaluate IP and other popular metrics such as Tokenization Parity (TP) and Tokenizer Fertility (TF) on several variants of open-sourced LLMs (Llama2, Gemma, Mistral). Among all metrics known to us, IP is better correlated with existing task-specific benchmark scores from the literature and thus better predicts such scores in a certain language. These findings show that IP may be useful for ranking multilingual LLMs' capabilities regardless of the downstream task."
}