Pith. sign in

REVIEW 4 cited by

SambaLingo: Teaching Large Language Models New Languages

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.05829 v2 pith:YBT2MCRK submitted 2024-04-08 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords languageslanguageacrossadaptationavailabilitybeenexistingllms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Despite the widespread availability of LLMs, there remains a substantial gap in their capabilities and availability across diverse languages. One approach to address these issues has been to take an existing pre-trained LLM and continue to train it on new languages. While prior works have experimented with language adaptation, many questions around best practices and methodology have not been covered. In this paper, we present a comprehensive investigation into the adaptation of LLMs to new languages. Our study covers the key components in this process, including vocabulary extension, direct preference optimization and the data scarcity problem for human alignment in low-resource languages. We scale these experiments across 9 languages and 2 parameter scales (7B and 70B). We compare our models against Llama 2, Aya-101, XGLM, BLOOM and existing language experts, outperforming all prior published baselines. Additionally, all evaluation code and checkpoints are made public to facilitate future research.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Mangosteen: An Open Thai Corpus for Language Model Pretraining

    cs.CL 2025-07 conditional novelty 6.0 of 10

    An open 47B-token Thai pre-training corpus and a Thai-adapted data cleaning pipeline, with ablations showing quality gains and an 8B model that improves on Thai benchmarks.

  2. ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data

    cs.CL 2024-12 conditional novelty 6.0 of 10

    ChatTime tokenizes time series as discrete foreign-language words, continually pre-trains and instruction-tunes LLaMA-2-7B via LoRA, and shows competitive zero-shot forecasting plus bimodal text and time series tasks.

  3. Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian

    cs.CL 2025-01 conditional novelty 5.0 of 10

    Pruning unused tokens from a multilingual encoder's vocabulary for Estonian preserves named-entity recognition F1 and cuts model size, while a retrained 32K tokenizer degrades performance under the tested training budget.

  4. The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

    cs.CL 2024-12 conditional novelty 5.0 of 10

    A code LLM learning a new language first translates through its dominant language's internal system, then builds a separate system; this pattern can guide optimal training data mixing.

Pith tools