{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T05:47:09Z","timestamp":1783144029230,"version":"3.54.6"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825615","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"6387-6393","source":"Crossref","is-referenced-by-count":5,"title":["Problematic Tokens: Tokenizer Bias in Large Language Models"],"prefix":"10.1109","author":[{"given":"Jin","family":"Yang","sequence":"first","affiliation":[{"name":"Syracuse University,Syracuse,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Florida Atlantic University,Boca Raton,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbin","family":"Lin","sequence":"additional","affiliation":[{"name":"Florida Atlantic University,Boca Raton,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunduo","family":"Zhao","sequence":"additional","affiliation":[{"name":"New York University,NYC,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref3","article-title":"Let\u2019s build the gpt tokenizer","author":"Karpathy","year":"2024"},{"key":"ref4","article-title":"Solidgoldmagikarp iii: Glitch token archaeology","author":"Watkins","year":"2023"},{"key":"ref5","article-title":"Solidgoldmagikarp (plus, prompt generation)","author":"Rumbelow","year":"2023"},{"key":"ref6","article-title":"A search for more chatgpt\/gpt-3.5\/gpt-4 \u201cunspeakable\u201d glitch tokens","author":"Fell","year":"2023"},{"key":"ref7","article-title":"Coercing llms to do and reveal (almost) anything","author":"Geiping","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.649"},{"key":"ref9","article-title":"Tokenization matters! degrading large language models through challenging their tokenization","author":"Wang","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1075\/ijchl.00023.yan"},{"key":"ref11","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref12","article-title":"Gpt-4o: Omni-capable multimodal model","year":"2024"},{"key":"ref13","article-title":"Problematictokens","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","location":"Washington, DC, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825615.pdf?arnumber=10825615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:03:55Z","timestamp":1737101035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825615","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}