Pith. sign in

REVIEW 9 cited by

Data Engineering for Scaling Language Models to 128K Context

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 2402.10171 v1 pith:5R3MAAJG submitted 2024-02-15 cs.CL cs.AI

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

We study the continual pretraining recipe for scaling language models' context lengths to 128K, with a focus on data engineering. We hypothesize that long context modeling, in particular \textit{the ability to utilize information at arbitrary input locations}, is a capability that is mostly already acquired through large-scale pretraining, and that this capability can be readily extended to contexts substantially longer than seen during training~(e.g., 4K to 128K) through lightweight continual pretraining on appropriate data mixture. We investigate the \textit{quantity} and \textit{quality} of the data for continual pretraining: (1) for quantity, we show that 500 million to 5 billion tokens are enough to enable the model to retrieve information anywhere within the 128K context; (2) for quality, our results equally emphasize \textit{domain balance} and \textit{length upsampling}. Concretely, we find that naively upsampling longer data on certain domains like books, a common practice of existing work, gives suboptimal performance, and that a balanced domain mixture is important. We demonstrate that continual pretraining of the full model on 1B-5B tokens of such data is an effective and affordable strategy for scaling the context length of language models to 128K. Our recipe outperforms strong open-source long-context models and closes the gap to frontier models like GPT-4 128K.

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. Full citation record

  1. Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE

    cs.LG 2026-07 accept novelty 6.0 of 10

    Jet-Long is a tuning-free bifocal RoPE method that dynamically sets remote group size from sequence length, recovering the base model within the pretrained window and beating prior zero-shot extenders on RULER, HELMET...

  2. Towards Compute-Optimal Many-Shot In-Context Learning

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Hybrid demonstration selection that adds 20 similar examples to a large cached random or k-means set matches or beats similarity-only selection at up to 10x lower estimated inference cost in many-shot ICL.

  3. SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A 7B writing model trained on plan-write-refine thinking data with multi-stage preference optimization matches or beats several larger models on long-form generation benchmarks.

  4. LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models

    cs.LG 2025-07 conditional novelty 5.0 of 10

    LaCache keeps a layer-dependent diagonal slice of the KV cache and iteratively compacts old entries, improving long-context perplexity and retrieval accuracy versus StreamingLLM at fixed cache sizes.

  5. SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks

    cs.CR 2025-06 conditional novelty 5.0 of 10

    SOFT paraphrases low-loss fine-tuning samples before training, reducing MIA AUC from about 0.82 to about 0.54 across six datasets at roughly 7% perplexity cost.

  6. Curse of High Dimensionality Issue in Transformer for Long-context Modeling

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A group attention mechanism that keeps important tokens and merges the rest cuts long-context decoding cost, but the theoretical case for grouping is only weakly supported.

  7. LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions

    cs.CL 2025-05 conditional novelty 5.0 of 10

    By prompting an aligned LLM with a document and the special token that precedes a user query, LongMagpie synthesizes long-context instruction data that outperforms prior datasets when used to fine-tune Llama-3-8B.

  8. Automated Essay Scoring Incorporating Annotations from Automated Feedback Systems

    cs.CL 2025-05 conditional novelty 4.0 of 10

    On the PERSUADE corpus, adding generated argument-component tags to essay text raised automated scoring agreement from a QWK of 0.860 to 0.868, while error-only tags lowered it.

  9. The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

    cs.AI 2026-06 unverdicted novelty 2.0 of 10

    A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.

Pith tools