Tracing Multilingual Factual Knowledge Acquisition in Pretraining

ACL ARR 2025 May Submission2783 Authors

Abstract:

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 crosslingual consistency throughout pretraining largely unexplored.
In this work, we trace how factual recall and crosslingual consistency evolve during pretraining, focusing on OLMo-7B as a case study.
We find that both accuracy and consistency improve over time for most languages.
We show that this improvement is primarily driven by the fact frequency in the pretraining corpus: more frequent facts are more likely to be recalled correctly, regardless of language.
Yet, some low-frequency facts in non-English languages can still be correctly recalled.
Our analysis reveals that these instances largely benefit from crosslingual transfer of their English counterparts -- an effect that emerges predominantly in the early stages of pretraining.
We pinpoint two distinct pathways through which multilingual factual knowledge acquisition occurs:
(1) $\textbf{\emph{frequency-driven learning}}$, which is dominant and language-agnostic, and (2) $\textbf{\emph{crosslingual transfer}}$, which is limited in scale and typically constrained to relation types involving named entities.
We will release our code to facilitate further research.

Paper Type: Long

Research Area: Multilingualism and Cross-Lingual NLP

Research Area Keywords: multilingualism, data influence, pre-training, cross-lingual transfer

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Data analysis

Languages Studied: Arabic, Catalan, Greek, English, Spanish, French, Japanese, Korean, Russian, Turkish, Ukrainian, Chinese

Submission Number: 2783