{"paper":{"title":"Efficient Pretraining Length Scaling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bohong Wu, Jianqiao Lu, Shen Yan, Sijun Zhang, Xun Zhou, Ya Wang, Yutao Zeng","submitted_at":"2025-04-21T09:41:26Z","abstract_excerpt":"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 depe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14992","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.14992/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}