Pith. sign in

REVIEW 5 cited by

Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language 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 2404.04167 v5 pith:VMBWP4ND submitted 2024-04-05 cs.CL cs.AI

Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model

classification cs.CL cs.AI
keywords chineselanguagebillionct-llmtokensenglishmodeltraining
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this study, we introduce CT-LLM, a 2B large language model (LLM) that illustrates a pivotal shift towards prioritizing the Chinese language in developing LLMs. Uniquely initiated from scratch, CT-LLM diverges from the conventional methodology by primarily incorporating Chinese textual data, utilizing an extensive corpus of 1,200 billion tokens, including 800 billion Chinese tokens, 300 billion English tokens, and 100 billion code tokens. This strategic composition facilitates the model's exceptional proficiency in understanding and processing Chinese, a capability further enhanced through alignment techniques. Demonstrating remarkable performance on the CHC-Bench, CT-LLM excels in Chinese language tasks, and showcases its adeptness in English through SFT. This research challenges the prevailing paradigm of training LLMs predominantly on English corpora and then adapting them to other languages, broadening the horizons for LLM training methodologies. By open-sourcing the full process of training a Chinese LLM, including a detailed data processing procedure with the obtained Massive Appropriate Pretraining Chinese Corpus (MAP-CC), a well-chosen multidisciplinary Chinese Hard Case Benchmark (CHC-Bench), and the 2B-size Chinese Tiny LLM (CT-LLM), we aim to foster further exploration and innovation in both academia and industry, paving the way for more inclusive and versatile language models.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Scaling Latent Reasoning via Looped Language Models

    cs.CL 2025-10 unverdicted novelty 7.0

    Looped language models with latent iterative computation and entropy-regularized depth allocation achieve performance matching up to 12B standard LLMs through superior knowledge manipulation.

  2. EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models

    cs.CL 2025-10 unverdicted novelty 6.0

    EvalMORAAL evaluates moral alignment of 20 LLMs on World Values Survey and PEW data, reporting high overall correlation with human responses but a 0.21 gap between Western and non-Western regions.

  3. Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning

    cs.LG 2026-05 unverdicted novelty 5.0

    PVPO is a sample-efficient RL method that improves semantic, geometric, and physical quality in LLM LEGO assembly generation by mitigating the PhysHack failure mode where validity alone fails to ensure fidelity.

  4. Scaling Latent Reasoning via Looped Language Models

    cs.CL 2025-10 conditional novelty 5.0

    A 1.4B and a 2.6B looped (weight-tied, recurrent-depth) language model trained on 7.7T tokens match or exceed several 4B–8B transformer baselines on selected reasoning benchmarks.

  5. Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices

    cs.DC 2025-03 unverdicted novelty 2.0

    Position paper claiming that distributed training across massive edge devices can overcome data depletion and centralized compute monopolies in LLM scaling.