{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:06Z","timestamp":1774419366135,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889733","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["LBPE: Long-token-first Tokenization to Improve Large Language Models"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Lian","sequence":"first","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhe","family":"Xiong","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijia","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Niu","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shasha","family":"Mo","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"8","key":"ref1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021"},{"key":"ref4","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref5","first-page":"2397","article-title":"Pythia: A suite for analyzing large language models across training and scaling","volume-title":"International Conference on Machine Learning","author":"Biderman"},{"key":"ref6","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref7","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2023"},{"key":"ref8","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref9","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref10","article-title":"Breaking the stage barrier: A novel single-stage approach to long context extension for large language models","author":"Lian","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.360"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.272"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3218830"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"issue":"2","key":"ref15","first-page":"23","article-title":"A new algorithm for data compression","volume":"12","author":"Gage","year":"1994","journal-title":"C Users Journal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.571"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.302"},{"key":"ref18","article-title":"Scaffold-bpe: Enhancing byte pair encoding with simple and effective scaffold token removal","author":"Lian","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.18"},{"key":"ref20","article-title":"Maskmoe: Boosting token-level learning via routing mask in mixture-of-experts","author":"Su","year":"2024"},{"key":"ref21","article-title":"The pile: An 800gb dataset of diverse text for language modeling","author":"Gao","year":"2020"},{"key":"ref22","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref23","article-title":"Temporal scaling law for large language models","author":"Xiong","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.505"},{"key":"ref25","article-title":"Boolq: Exploring the surprising difficulty of natural yes\/no questions","author":"Clark","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1454"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n16-1098"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref32","article-title":"Baichuan-7b","year":"2023"},{"key":"ref33","article-title":"Baichuan-13b","year":"2023"},{"key":"ref34","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889733.pdf?arnumber=10889733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:31Z","timestamp":1774416151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889733","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}