Pith. sign in

REVIEW 9 cited by

Skywork: A More Open Bilingual Foundation Model

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 2310.19341 v1 pith:SZKLXFLN submitted 2023-10-30 cs.CL cs.AI

classification cs.CLcs.AI
keywords corpustrainingchinesellmsmodelopenskywork-13bbilingual
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3.2 trillion tokens drawn from both English and Chinese texts. This bilingual foundation model is the most extensively trained and openly published LLMs of comparable size to date. We introduce a two-stage training methodology using a segmented corpus, targeting general purpose training and then domain-specific enhancement training, respectively. We show that our model not only excels on popular benchmarks, but also achieves \emph{state of the art} performance in Chinese language modeling on diverse domains. Furthermore, we propose a novel leakage detection method, demonstrating that test data contamination is a pressing issue warranting further investigation by the LLM community. To spur future research, we release Skywork-13B along with checkpoints obtained during intermediate stages of the training process. We are also releasing part of our SkyPile corpus, a collection of over 150 billion tokens of web text, which is the largest high quality open Chinese pre-training corpus to date. We hope Skywork-13B and our open corpus will serve as a valuable open-source resource to democratize access to high-quality LLMs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 11 citations worldwide. Full citation record

  1. Phi-Ground Tech Report: Advancing Perception in GUI Grounding

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Phi-Ground models achieve state-of-the-art click accuracy on five GUI grounding benchmarks for models under 10B parameters using a 40M-sample training recipe with text-first inputs, random-resize augmentation, uniform...

  2. Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A multilingual LLM training method that groups similar languages, converts high-deviation layers into mixture-of-experts layers, and assigns one expert per language group improves perplexity across 18 to 128 languages.

  3. OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics

    cs.AI 2025-06 conditional novelty 6.0 of 10

    A private, contamination-resistant benchmark of 250 olympiad-level programming problems shows top reasoning models reaching about 36% solve rates, far above conventional models.

  4. TokAlign: Efficient Vocabulary Adaptation via Token Alignment

    cs.CL 2025-06 conditional novelty 6.0 of 10

    TokAlign aligns source and target BPE token vocabularies using GloVe co-occurrence embeddings and re-initializes LLM embeddings, recovering within 5k steps and enabling token-level distillation.

  5. Index SLM Technical Report

    cs.CL 2026-07 accept novelty 5.0 of 10

    Index-1.9B-Base reaches 64.92 average benchmark score via WSD training with late curated data plus Norm-Head, with open Pure/Boost controls isolating instruction-data inflation.

  6. Assessing the Role of Data Quality in Training Bilingual Language Models

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A quality filter trained only on English labels can select better French, German, and Chinese pretraining data, improving bilingual model performance and cutting the monolingual-bilingual gap to about 1%.

  7. Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-Experts

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A layer-wise expert allocation algorithm based on hidden-state similarity, plus a routing classifier, improves parameter efficiency and reduces forgetting when expanding LLMs to new languages.

  8. From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Fine-tuning TTS models on tens of hours of real audio enables generation of 500,000 hours of synthetic speech that reduces ASR error rates by over 30% on Whisper-large-v3.

  9. From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI

    cs.AI 2026-06 conditional novelty 4.0 of 10

    Autonomous AI becomes dependable when tool use is embedded in persistent workspaces with reusable skills, shifting evaluation from answers to task closure.

Pith tools