{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T13:11:14Z","timestamp":1774703474826,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650513","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["Baichuan2-Sum: Instruction Finetune Baichuan2-7B Model for Dialogue Summarization"],"prefix":"10.1109","author":[{"given":"Jianfei","family":"Xiao","sequence":"first","affiliation":[{"name":"University of Southern California,Viterbi School of Engineering,Los Angeles,United States"}]},{"given":"Yancan","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore,School of Computing,Singapore,Singapore"}]},{"given":"Yimin","family":"Ou","sequence":"additional","affiliation":[{"name":"Cornell University,College of Computing and Information Science,New York,United States"}]},{"given":"Hanyi","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Southern California,Viterbi School of Engineering,Los Angeles,United States"}]},{"given":"Kai","family":"Shu","sequence":"additional","affiliation":[{"name":"University of Southern California,Viterbi School of Engineering,Los Angeles,United States"}]},{"given":"Yiyong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Taiyuan Normal University,Computer Science College,Guangzhou,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.365"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.117"},{"key":"ref4","first-page":"17","article-title":"Dialogue discourse-aware graph convolutional networks for abstractive meeting summarization[J]","author":"Feng","year":"2020"},{"key":"ref5","first-page":"43","article-title":"Towards Modeling Role-Aware Centrality for Dialogue Summarization[C]","volume-title":"Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing","author":"Liang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.182"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17724"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21432"},{"key":"ref10","first-page":"1073","article-title":"Get to the point: Summarization with pointer-generator networks[C]","volume-title":"Proc. Conf. Annu. Meeting Assoc. Comput. Linguistics (ACL)","author":"Liu"},{"key":"ref11","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding[C]","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref13","first-page":"1877","article-title":"Language models are few-shot learners[J]","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Llama 2: Open foundation and fine-tuned chat models[J]","author":"Touvron","year":"2023","journal-title":"ar**v preprint ar**v:2307.09288"},{"key":"ref15","article-title":"Baichuan 2: Open large-scale language models[J]","author":"Yang","year":"2023"},{"key":"ref16","article-title":"Glm: General language model pretraining with autoregressive blank infilling[J]","author":"Du","year":"2021","journal-title":"ar**v preprint ar**v:2103.10360"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5409"},{"key":"ref18","article-title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning[J]","author":"Jain","year":"2023"},{"key":"ref19","article-title":"Bloom: A 176b-parameter open-access multilingual language model[J]","author":"Workshop","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref25","author":"Shazeer","year":"2020","journal-title":"Glu variants improve transformer[J]"},{"key":"ref26","author":"Rabe","year":"2021","journal-title":"Self-attention Does Not Need O(n2) Memory[J]"},{"key":"ref27","first-page":"32","article-title":"Root mean square layer normalization[J]","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries[C]","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref29","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation[C]","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni"},{"key":"ref30","article-title":"Bertscore: Evaluating text generation with bert[J]","author":"Zhang","year":"2019"},{"key":"ref31","author":"Hu","year":"2021","journal-title":"LoRA: Low-Rank Adaptation of Large Language Models[J]"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref36","article-title":"Alpacafarm: A simulation framework for methods that learn from human feedback[J]","author":"Dubois","year":"2023"},{"key":"ref37","article-title":"Llama 2: Open foundation and fine-tuned chat models[J]","author":"Touvron","year":"2023"},{"key":"ref38","article-title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning[J]","author":"Jain","year":"2023"},{"key":"ref39","article-title":"Enhance model\u2019s performances using NEFTune","author":"Face","year":"2023"},{"key":"ref40","first-page":"30","article-title":"Attention is all you need[J]","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650513.pdf?arnumber=10650513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:25:39Z","timestamp":1725945939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650513\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650513","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}