{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:47:24Z","timestamp":1765500444232,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761096","type":"proceedings-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T18:37:32Z","timestamp":1762799852000},"page":"4346-4356","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5069-8840","authenticated-orcid":false,"given":"Haokun","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8380-2905","authenticated-orcid":false,"given":"Jinyi","family":"Han","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7413-6735","authenticated-orcid":false,"given":"Jie","family":"Shi","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0333-6073","authenticated-orcid":false,"given":"Chengyu","family":"Du","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0670-5602","authenticated-orcid":false,"given":"Jiaqing","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8403-9591","authenticated-orcid":false,"given":"Yanghua","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8595-534X","authenticated-orcid":false,"given":"Weikang","family":"Zhou","sequence":"additional","affiliation":[{"name":"ANT GROUP, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8449-9318","authenticated-orcid":false,"given":"Zeye","family":"Sun","sequence":"additional","affiliation":[{"name":"ANT GROUP, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0580-0371","authenticated-orcid":false,"given":"Fei","family":"Yu","sequence":"additional","affiliation":[{"name":"ANT GROUP, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AI@Meta. 2024. Llama 3 Model Card. https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_2_1_2_1","unstructured":"Shengnan An Zexiong Ma Zeqi Lin Nanning Zheng Jian-Guang Lou and Weizhu Chen. 2024. Learning From Mistakes Makes LLM Better Reasoner. arXiv:2310.20689 [cs.CL]"},{"key":"e_1_3_2_1_3_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arXiv:2309.16609 [cs.CL]"},{"key":"e_1_3_2_1_4_1","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et al. 2023. A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology (2023)."},{"key":"e_1_3_2_1_5_1","unstructured":"Kai Chen Chunwei Wang Kuo Yang Jianhua Han Lanqing Hong Fei Mi Hang Xu Zhengying Liu Wenyong Huang Zhenguo Li et al. 2023. Gaining wisdom from setbacks: Aligning large language models via mistake analysis. arXiv preprint arXiv:2310.10477 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Daixuan Cheng Yuxian Gu Shaohan Huang Junyu Bi Minlie Huang and Furu Wei. 2024a. Instruction Pre-Training: Language Models are Supervised Multitask Learners. arXiv:2406.14491 [cs.CL] https:\/\/arxiv.org\/abs\/2406.14491","DOI":"10.18653\/v1\/2024.emnlp-main.148"},{"key":"e_1_3_2_1_7_1","unstructured":"Daixuan Cheng Shaohan Huang and Furu Wei. 2024b. Adapting Large Language Models via Reading Comprehension. arXiv:2309.09530 [cs.CL]"},{"key":"e_1_3_2_1_8_1","volume-title":"Training Verifiers to Solve Math Word Problems. CoRR","author":"Cobbe Karl","year":"2021","unstructured":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. CoRR, Vol. abs\/2110.14168 (2021). arXiv:2110.14168 https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Andrea Cossu Tinne Tuytelaars Antonio Carta Lucia Passaro Vincenzo Lomonaco and Davide Bacciu. 2022. Continual Pre-Training Mitigates Forgetting in Language and Vision. arXiv:2205.09357 [cs.CL]","DOI":"10.2139\/ssrn.4495233"},{"key":"e_1_3_2_1_10_1","volume-title":"The Faiss library. ArXiv","author":"Douze Matthijs","year":"2024","unstructured":"Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazar'e, Maria Lomeli, Lucas Hosseini, and Herv'e J'egou. 2024. The Faiss library. ArXiv, Vol. abs\/2401.08281 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267028372"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Zorik Gekhman Gal Yona Roee Aharoni Matan Eyal Amir Feder Roi Reichart and Jonathan Herzig. 2024. Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations? arXiv:2405.05904 [cs.CL]","DOI":"10.18653\/v1\/2024.emnlp-main.444"},{"key":"e_1_3_2_1_12_1","volume-title":"Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation. arXiv:2306.05783 [cs.CL]","author":"Gu Zhouhong","year":"2023","unstructured":"Zhouhong Gu, Xiaoxuan Zhu, Haoning Ye, Lin Zhang, Jianchen Wang, Sihang Jiang, Zhuozhi Xiong, Zihan Li, Qianyu He, Rui Xu, Wenhao Huang, Zili Wang, Shusen Wang, Weiguo Zheng, Hongwei Feng, and Yanghua Xiao. 2023. Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation. arXiv:2306.05783 [cs.CL]"},{"key":"e_1_3_2_1_13_1","volume-title":"Continual pre-training of large language models: How to (re) warm your model? arXiv preprint arXiv:2308.04014","author":"Gupta Kshitij","year":"2023","unstructured":"Kshitij Gupta, Benjamin Th\u00e9rien, Adam Ibrahim, Mats L Richter, Quentin Anthony, Eugene Belilovsky, Irina Rish, and Timoth\u00e9e Lesort. 2023. Continual pre-training of large language models: How to (re) warm your model? arXiv preprint arXiv:2308.04014 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.95"},{"key":"e_1_3_2_1_16_1","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et al. 2023b. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. ArXiv preprint Vol. abs\/2311.05232 (2023). https:\/\/arxiv.org\/abs\/2311.05232"},{"key":"e_1_3_2_1_17_1","unstructured":"Yuzhen Huang Yuzhuo Bai Zhihao Zhu Junlei Zhang Jinghan Zhang Tangjun Su Junteng Liu Chuancheng Lv Yikai Zhang Jiayi Lei Yao Fu Maosong Sun and Junxian He. 2023a. C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.418"},{"key":"e_1_3_2_1_19_1","volume-title":"Wen tau Yih, and Srinivasan Iyer.","author":"Jiang Zhengbao","year":"2024","unstructured":"Zhengbao Jiang, Zhiqing Sun, Weijia Shi, Pedro Rodriguez, Chunting Zhou, Graham Neubig, Xi Victoria Lin, Wen tau Yih, and Srinivasan Iyer. 2024. Instruction-tuned Language Models are Better Knowledge Learners. arXiv:2402.12847 [cs.CL]"},{"key":"e_1_3_2_1_20_1","volume-title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora. arXiv:2110.08534 [cs.CL]","author":"Jin Xisen","year":"2022","unstructured":"Xisen Jin, Dejiao Zhang, Henghui Zhu, Wei Xiao, Shang-Wen Li, Xiaokai Wei, Andrew Arnold, and Xiang Ren. 2022. Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora. arXiv:2110.08534 [cs.CL]"},{"key":"e_1_3_2_1_21_1","unstructured":"Zixuan Ke Yijia Shao Haowei Lin Tatsuya Konishi Gyuhak Kim and Bing Liu. 2023. Continual Pre-training of Language Models. arXiv:2302.03241 [cs.CL]"},{"key":"e_1_3_2_1_22_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_23_1","volume-title":"Jacob Mitchell Springer, and Aditi Raghunathan","author":"Kotha Suhas","year":"2024","unstructured":"Suhas Kotha, Jacob Mitchell Springer, and Aditi Raghunathan. 2024. Understanding Catastrophic Forgetting in Language Models via Implicit Inference. arXiv:2309.10105 [cs.CL]"},{"key":"e_1_3_2_1_24_1","volume-title":"Manzil Zaheer, Xin Wang, Michal Lukasik, Andreas Veit, Felix Yu, and Sanjiv Kumar.","author":"Li Daliang","year":"2022","unstructured":"Daliang Li, Ankit Singh Rawat, Manzil Zaheer, Xin Wang, Michal Lukasik, Andreas Veit, Felix Yu, and Sanjiv Kumar. 2022. Large language models with controllable working memory. ArXiv preprint, Vol. abs\/2211.05110 (2022). https:\/\/arxiv.org\/abs\/2211.05110"},{"key":"e_1_3_2_1_25_1","volume-title":"CMMLU: Measuring massive multitask language understanding in Chinese. arXiv:2306.09212 [cs.CL]","author":"Li Haonan","year":"2024","unstructured":"Haonan Li, Yixuan Zhang, Fajri Koto, Yifei Yang, Hai Zhao, Yeyun Gong, Nan Duan, and Timothy Baldwin. 2024b. CMMLU: Measuring massive multitask language understanding in Chinese. arXiv:2306.09212 [cs.CL]"},{"key":"e_1_3_2_1_26_1","volume-title":"Conan-embedding: General Text Embedding with More and Better Negative Samples. arXiv:2408.15710 [cs.CL] https:\/\/arxiv.org\/abs\/2408.15710","author":"Li Shiyu","year":"2024","unstructured":"Shiyu Li, Yang Tang, Shizhe Chen, and Xi Chen. 2024a. Conan-embedding: General Text Embedding with More and Better Negative Samples. arXiv:2408.15710 [cs.CL] https:\/\/arxiv.org\/abs\/2408.15710"},{"key":"e_1_3_2_1_27_1","volume-title":"Yuncheng Huang, Wenhao Huang, Xintao Wang, Lida Chen, Haixia Han, Jie Shi, Tinghui Zhu, Yidan Xu, Shisong Chen, Zhouhong Gu, and Yanghua Xiao.","author":"Liang Jiaqing","year":"2023","unstructured":"Jiaqing Liang, Qianyu He, Yikai Zhang Yipei Xu, Yuncheng Huang, Wenhao Huang, Xintao Wang, Lida Chen, Haixia Han, Jie Shi, Tinghui Zhu, Yidan Xu, Shisong Chen, Zhouhong Gu, and Yanghua Xiao. 2023. CuteGPT: Towards a Useful Chinese Large Language Model. https:\/\/github.com\/Abbey4799\/cuteGPT."},{"key":"e_1_3_2_1_28_1","unstructured":"Shirong Ma Shen Huang Shulin Huang Xiaobin Wang Yangning Li Hai-Tao Zheng Pengjun Xie Fei Huang and Yong Jiang. 2023. EcomGPT-CT: Continual Pre-training of E-commerce Large Language Models with Semi-structured Data. arXiv:2312.15696 [cs.CL]"},{"key":"e_1_3_2_1_29_1","unstructured":"Baolin Peng Chunyuan Li Pengcheng He Michel Galley and Jianfeng Gao. 2023. Instruction Tuning with GPT-4. arXiv:2304.03277 [cs.CL]"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_32_1","volume-title":"Jing Liu, Hao Tian, Hua Wu, Ji-Rong Wen, and Haifeng Wang.","author":"Ren Ruiyang","year":"2023","unstructured":"Ruiyang Ren, Yuhao Wang, Yingqi Qu, Wayne Xin Zhao, Jing Liu, Hao Tian, Hua Wu, Ji-Rong Wen, and Haifeng Wang. 2023. Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation. arXiv:2307.11019 [cs.CL]"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Yu Sun Shuohuan Wang Yukun Li Shikun Feng Hao Tian Hua Wu and Haifeng Wang. 2019. ERNIE 2.0: A Continual Pre-training Framework for Language Understanding. arXiv:1907.12412 [cs.CL]","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"e_1_3_2_1_34_1","volume-title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models. arXiv:2310.06762 [cs.CL]","author":"Wang Xiao","year":"2023","unstructured":"Xiao Wang, Yuansen Zhang, Tianze Chen, Songyang Gao, Senjie Jin, Xianjun Yang, Zhiheng Xi, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, and Xuanjing Huang. 2023. TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models. arXiv:2310.06762 [cs.CL]"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Yifan Wang Yafei Liu Chufan Shi Haoling Li Chen Chen Haonan Lu and Yujiu Yang. 2024. InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions. arXiv:2403.11435 [cs.CL]","DOI":"10.18653\/v1\/2024.naacl-long.37"},{"key":"e_1_3_2_1_36_1","volume-title":"Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022. Finetuned Language Models Are Zero-Shot Learners. arXiv:2109.01652 [cs.CL]"},{"key":"e_1_3_2_1_37_1","unstructured":"Tongtong Wu Linhao Luo Yuan-Fang Li Shirui Pan Thuy-Trang Vu and Gholamreza Haffari. 2024. Continual Learning for Large Language Models: A Survey. arXiv:2402.01364 [cs.CL]"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Yong Xie Karan Aggarwal and Aitzaz Ahmad. 2023. Efficient Continual Pre-training for Building Domain Specific Large Language Models. arXiv:2311.08545 [cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.606"},{"key":"e_1_3_2_1_39_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/D18-1259"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Hanning Zhang Shizhe Diao Yong Lin Yi R. Fung Qing Lian Xingyao Wang Yangyi Chen Heng Ji and Tong Zhang. 2024. R-Tuning: Instructing Large Language Models to Say `I Don't Know'. arXiv:2311.09677 [cs.CL]","DOI":"10.18653\/v1\/2024.naacl-long.394"},{"key":"e_1_3_2_1_42_1","volume-title":"CITB: A Benchmark for Continual Instruction Tuning. arXiv:2310.14510 [cs.CL]","author":"Zhang Zihan","year":"2023","unstructured":"Zihan Zhang, Meng Fang, Ling Chen, and Mohammad-Reza Namazi-Rad. 2023a. CITB: A Benchmark for Continual Instruction Tuning. arXiv:2310.14510 [cs.CL]"},{"key":"e_1_3_2_1_43_1","volume-title":"How do large language models capture the ever-changing world knowledge? a review of recent advances. ArXiv preprint","author":"Zhang Zihan","year":"2023","unstructured":"Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad, and Jun Wang. 2023b. How do large language models capture the ever-changing world knowledge? a review of recent advances. ArXiv preprint, Vol. abs\/2310.07343 (2023). https:\/\/arxiv.org\/abs\/2310.07343"},{"key":"e_1_3_2_1_44_1","volume-title":"LIMA: Less Is More for Alignment. arXiv:2305.11206 [cs.CL]","author":"Zhou Chunting","year":"2023","unstructured":"Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, and Omer Levy. 2023. LIMA: Less Is More for Alignment. arXiv:2305.11206 [cs.CL]"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:44:49Z","timestamp":1765500289000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":44,"alternative-id":["10.1145\/3746252.3761096","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761096","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}