HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization

• URL: http://arxiv.org/abs/2504.21018v2
• Date: Fri, 11 Jul 2025 23:05:26 GMT
• Title: HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization
• Authors: Enes Özeren, Yihong Liu, Hinrich Schütze,
• Abstract summary: Many pre-trained language models (PLMs) exhibit suboptimal performance on mid- and low-resource languages.<n>A common strategy to address this is to introduce new tokens specific to the target languages, initialize their embeddings, and apply continual pre-training on target-language data.<n>We propose HYPEROFA, a hypernetwork-based approach for more adaptive token embedding.
• Score: 50.27950279695363
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many pre-trained language models (PLMs) exhibit suboptimal performance on mid- and low-resource languages, largely due to limited exposure to these languages during pre-training. A common strategy to address this is to introduce new tokens specific to the target languages, initialize their embeddings, and apply continual pre-training on target-language data. Among such methods, OFA (Liu et al., 2024a) proposes a similarity-based subword embedding initialization heuristic that is both effective and efficient. However, OFA restricts target-language token embeddings to be convex combinations of a fixed number of source-language embeddings, which may limit expressiveness. To overcome this limitation, we propose HYPEROFA, a hypernetwork-based approach for more adaptive token embedding initialization. The hypernetwork is trained to map from an external multilingual word vector space to the PLMs token embedding space using source-language tokens. Once trained, it can generate flexible embeddings for target-language tokens, serving as a good starting point for continual pretraining. Experiments demonstrate that HYPEROFA consistently outperforms random initialization baseline and matches or exceeds the performance of OFA in both continual pre-training convergence and downstream task performance. We make the code publicly available.

Related papers

• MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization [81.83460411131931]
  In multilingual settings, non-Latin scripts and low-resource languages are usually disadvantaged in terms of language models' utility, efficiency, and cost. We propose multilingual adaptive gradient-based tokenization to reduce over-segmentation via adaptive gradient-based subword tokenization.
  arXiv  Detail & Related papers  (2024-07-11T18:59:21Z)
• An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models [31.231720803637085]
  Language Models (LMs) excel in natural language processing tasks for English but show reduced performance in most other languages. limited vocabulary coverage in the original model's tokenizer leads to inadequate representation of new languages. Constrained Word2Vec (CW2V) does not require cross-lingual embeddings.
  arXiv  Detail & Related papers  (2024-07-08T11:38:49Z)
• How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text? [38.1823640848362]
  Large language models (LLMs) have shown remarkable capabilities in many languages beyond English. LLMs require more inference steps when generating non-English text due to their reliance on English-centric tokenizers and vocabulary. Vocabulary expansion with target language tokens is a widely used cross-lingual vocabulary adaptation approach to remedy this issue.
  arXiv  Detail & Related papers  (2024-06-17T12:42:34Z)
• OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining [49.213120730582354]
  Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary extension and continued pretraining. We propose a novel framework: $textbfO$ne $textbfF$or $textbfA$ll, which wisely initializes the embeddings of unseen subwords and thus can adapt a PLM to multiple languages efficiently and effectively.
  arXiv  Detail & Related papers  (2023-11-15T10:40:45Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models [26.598115320351496]
  FOCUS represents newly added tokens as combinations of tokens in the overlap of the source and target vocabularies. We focus our study on using the multilingual XLM-R as a source model.
  arXiv  Detail & Related papers  (2023-05-23T19:21:53Z)
• Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM [31.25193238045053]
  We introduce a novel method, namely GenCo, which leverages the strong generative power of large language models to assist in training a smaller language model. In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways. It helps crafting additional high-quality training pairs, by rewriting input texts conditioned on predicted labels.
  arXiv  Detail & Related papers  (2023-04-24T07:35:38Z)
• Bridging the Gap between Language Models and Cross-Lingual Sequence Labeling [101.74165219364264]
  Large-scale cross-lingual pre-trained language models (xPLMs) have shown effectiveness in cross-lingual sequence labeling tasks. Despite the great success, we draw an empirical observation that there is a training objective gap between pre-training and fine-tuning stages. In this paper, we first design a pre-training task tailored for xSL named Cross-lingual Language Informative Span Masking (CLISM) to eliminate the objective gap. Second, we present ContrAstive-Consistency Regularization (CACR), which utilizes contrastive learning to encourage the consistency between representations of input parallel
  arXiv  Detail & Related papers  (2022-04-11T15:55:20Z)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.