{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:44Z","timestamp":1774419644136,"version":"3.50.1"},"reference-count":45,"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\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017413","name":"Innovation Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017413","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\/icassp49660.2025.10888877","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["A Weighted Cross-entropy Loss for Mitigating LLM Hallucinations in Cross-lingual Continual Pretraining"],"prefix":"10.1109","author":[{"given":"Yuantao","family":"Fan","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruifan","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuan","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Introducing chatgpt","year":"2022"},{"key":"ref2","year":"2024","journal-title":"Gpt-4 technical report"},{"key":"ref3","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref4","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref5","author":"Jiang","year":"2023","journal-title":"Mistral 7b"},{"key":"ref6","year":"2024","journal-title":"Gemma: Open models based on gemini research and technology"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.217"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.612"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.68"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.48"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.706"},{"key":"ref12","article-title":"Not all tokens are what you need for pretraining","author":"Lin","year":"2024","journal-title":"NeuIPS"},{"key":"ref13","first-page":"4560","article-title":"Noisy exemplars make large language models more robust: A domain-agnostic behavioral analysis","author":"Zhang","year":"2023","journal-title":"EMNLP"},{"key":"ref14","first-page":"53983","article-title":"D4: Improving llm pretraining via document de-duplication and diversification","volume-title":"NeurIPS","author":"Tirumala"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"NeurIPS","author":"Brown"},{"key":"ref16","article-title":"PMI-masking: Principled masking of correlated spans","volume-title":"ICLR","author":"Levine"},{"key":"ref17","first-page":"23803","article-title":"Cross-entropy loss functions: Theoretical analysis and applications","volume-title":"ICML","author":"Mao"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"key":"ref19","author":"Du","year":"2024","journal-title":"Chinese tiny llm: Pretraining a chinese-centric large language model"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref21","article-title":"Introducing mpt-7b: A new standard for open-source, commercially usable llms","year":"2023"},{"key":"ref22","first-page":"79155","article-title":"The refinedweb dataset for falcon llm: Outperforming curated corpora with web data only","volume-title":"NeurIPS","author":"Penedo"},{"key":"ref23","first-page":"62991","article-title":"C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models","volume-title":"NeurIPS","author":"Huang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.149"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.671"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"ref29","article-title":"KoLA: Carefully benchmarking world knowledge of large language models","volume-title":"ICLR","author":"Yu"},{"key":"ref30","article-title":"Measuring massive multitask language understanding","volume-title":"ICLR","author":"Hendrycks"},{"key":"ref31","article-title":"Aligning ai with shared human values","volume-title":"ICLR","author":"Hendrycks"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"ref33","article-title":"GPQA: A graduate-level google-proof q&a benchmark","author":"Rein","year":"2024","journal-title":"COLM"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.489"},{"key":"ref35","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref36","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"TMLR"},{"key":"ref37","article-title":"Continual pre-training of language models","volume-title":"ICLR","author":"Ke"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.551"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00667"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.464"},{"key":"ref41","first-page":"49025","article-title":"Realtime qa: What\u2019s the answer right now?","volume-title":"NeurIPS","author":"Kasai"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07421-0"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.165"},{"key":"ref45","author":"Elaraby","year":"2023","journal-title":"Halo: Estimation and reduction of hallucinations in open-source weak large language models"}],"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\/10888877.pdf?arnumber=10888877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:54Z","timestamp":1774416234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888877","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}