Pith. sign in

REVIEW 4 cited by

Efficient Pretraining Length Scaling

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 2504.14992 v2 pith:4ZVIP2LD submitted 2025-04-21 cs.CL

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

Recent advances in large language models have demonstrated the effectiveness of length scaling during post-training, yet its potential in pre-training remains underexplored. We present the Parallel Hidden Decoding Transformer (\textit{PHD}-Transformer), a novel framework that enables efficient length scaling during pre-training while maintaining inference efficiency. \textit{PHD}-Transformer achieves this through an innovative KV cache management strategy that distinguishes between original tokens and hidden decoding tokens. By retaining only the KV cache of original tokens for long-range dependencies while immediately discarding hidden decoding tokens after use, our approach maintains the same KV cache size as the vanilla transformer while enabling effective length scaling. To further enhance performance, we introduce two optimized variants: \textit{PHD-SWA} employs sliding window attention to preserve local dependencies, while \textit{PHD-CSWA} implements chunk-wise sliding window attention to eliminate linear growth in pre-filling time. Extensive experiments demonstrate consistent improvements across multiple benchmarks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

    cs.CL 2026-05 conditional novelty 7.0 of 10

    Scratchpad Patching decouples compute from patch size in byte-level language models by inserting entropy-triggered scratchpads to update patch context dynamically.

  2. Scaling Latent Reasoning via Looped Language Models

    cs.CL 2025-10 unverdicted novelty 7.0 of 10

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

  3. The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

    cs.AI 2026-04 accept novelty 5.0 of 10

    A large survey organizes latent-space work in language-based models by foundation, evolution, four mechanisms, seven abilities, and open challenges.

  4. Scaling Latent Reasoning via Looped Language Models

    cs.CL 2025-10 conditional novelty 5.0 of 10

    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.

Pith tools