{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:06:16Z","timestamp":1784138776773,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808516","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"5060-5066","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Code-Based English Models Reveal Surprising Performance on Chinese QA Pair Extraction Task"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9428-4938","authenticated-orcid":false,"given":"Jiajun","family":"Yu","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8413-9726","authenticated-orcid":false,"given":"Linghan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0949-2150","authenticated-orcid":false,"given":"Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5366-3702","authenticated-orcid":false,"given":"Jiayuan","family":"Dong","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8876-9859","authenticated-orcid":false,"given":"Yue","family":"Shen","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4829-0751","authenticated-orcid":false,"given":"Zhiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5625-9204","authenticated-orcid":false,"given":"Yaozhen","family":"Liang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1664-6425","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1617-0920","authenticated-orcid":false,"given":"Haishuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Synthetic QA corpora generation with roundtrip consistency. arXiv preprint arXiv:1906.05416","author":"Alberti Chris","year":"2019","unstructured":"Chris Alberti, Daniel Andor, Emily Pitler, Jacob Devlin, and Michael Collins. 2019. Synthetic QA corpora generation with roundtrip consistency. arXiv preprint arXiv:1906.05416 (2019)."},{"key":"e_1_3_2_1_3_1","volume-title":"On the Cross-lingual Transferability of Monolingual Representations. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:204901567","author":"Artetxe Mikel","year":"2019","unstructured":"Mikel Artetxe, Sebastian Ruder, and Dani Yogatama. 2019. On the Cross-lingual Transferability of Monolingual Representations. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:204901567"},{"key":"e_1_3_2_1_4_1","unstructured":"DeepSeek-AI Xiao Bi Deli Chen Guanting Chen Shanhuang Chen Damai Dai Chengqi Deng Honghui Ding Kai Dong Qiushi Du Zhe Fu Huazuo Gao Kaige Gao Wenjun Gao Ruiqi Ge Kang Guan Daya Guo Jianzhong Guo Guangbo Hao Zhewen Hao Ying He Wenjie Hu Panpan Huang Erhang Li Guowei Li Jiashi Li Yao Li Y. K. Li Wenfeng Liang Fangyun Lin A. X. Liu Bo Liu Wen Liu Xiaodong Liu Xin Liu Yiyuan Liu Haoyu Lu Shanghao Lu Fuli Luo Shirong Ma Xiaotao Nie Tian Pei Yishi Piao Junjie Qiu Hui Qu Tongzheng Ren Zehui Ren Chong Ruan Zhangli Sha Zhihong Shao Junxiao Song Xuecheng Su Jingxiang Sun Yaofeng Sun Min Tang Bingxuan Wang Peiyi Wang Shiyu Wang Yaohui Wang Yongji Wang Tong Wu Y. Wu Xin Xie Zhenda Xie Ziwei Xie Yiliang Xiong Hanwei Xu R. X. Xu Yanhong Xu Dejian Yang Yu mei You Shuiping Yu Xingkai Yu B. Zhang Haowei Zhang Lecong Zhang Liyue Zhang Mingchuan Zhang Minghua Zhang Wentao Zhang Yichao Zhang Chenggang Zhao Yao Zhao Shangyan Zhou Shunfeng Zhou Qihao Zhu and Yuheng Zou. 2024. DeepSeek LLM: Scaling Open-Source Language Models with Longtermism. ArXiv (2024). https:\/\/arxiv.org\/abs\/2401.02954"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02865"},{"key":"e_1_3_2_1_6_1","volume-title":"Onestop qamaker: extract question-answer pairs from text in a one-stop approach. arXiv preprint arXiv:2102.12128","author":"Cui Shaobo","year":"2021","unstructured":"Shaobo Cui, Xintong Bao, Xinxing Zu, Yangyang Guo, Zhongzhou Zhao, Ji Zhang, and Haiqing Chen. 2021. Onestop qamaker: extract question-answer pairs from text in a one-stop approach. arXiv preprint arXiv:2102.12128 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca. arXiv preprint arXiv:2304.08177","author":"Cui Yiming","year":"2023","unstructured":"Yiming Cui, Ziqing Yang, and Xin Yao. 2023. Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca. arXiv preprint arXiv:2304.08177 (2023). https:\/\/arxiv.org\/abs\/2304.08177"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1177"},{"key":"e_1_3_2_1_9_1","volume-title":"Learning to ask: Neural question generation for reading comprehension. arXiv preprint arXiv:1705.00106","author":"Du Xinya","year":"2017","unstructured":"Xinya Du, Junru Shao, and Claire Cardie. 2017. Learning to ask: Neural question generation for reading comprehension. arXiv preprint arXiv:1705.00106 (2017)."},{"key":"e_1_3_2_1_10_1","volume-title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages. ArXiv","author":"Feng Zhangyin","year":"2020","unstructured":"Zhangyin Feng, Daya Guo, Duyu Tang, Nan Duan, Xiaocheng Feng, Ming Gong, Linjun Shou, Bing Qin, Ting Liu, Daxin Jiang, and Ming Zhou. 2020. CodeBERT: A Pre-Trained Model for Programming and Natural Languages. ArXiv, Vol. abs\/2002.08155 (2020). https:\/\/arxiv.org\/abs\/2002.08155"},{"key":"e_1_3_2_1_11_1","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yixin Dai Jiawei Sun Haofen Wang Haofen Wang et al. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997 Vol. 2 1 (2023) 32."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.535"},{"key":"e_1_3_2_1_14_1","unstructured":"Binyuan Hui Jian Yang Zeyu Cui Jiaxi Yang Dayiheng Liu Lei Zhang Tianyu Liu Jiajun Zhang Bowen Yu Kai Dang et al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.495"},{"key":"e_1_3_2_1_16_1","volume-title":"Scaling Laws for Neural Language Models. ArXiv","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, T. J. Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeff Wu, and Dario Amodei. 2020. Scaling Laws for Neural Language Models. ArXiv, Vol. abs\/2001.08361 (2020). https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1224"},{"key":"e_1_3_2_1_18_1","volume-title":"Cross-lingual Language Model Pretraining. ArXiv","author":"Lample Guillaume","year":"2019","unstructured":"Guillaume Lample and Alexis Conneau. 2019. Cross-lingual Language Model Pretraining. ArXiv, Vol. abs\/1901.07291 (2019). https:\/\/arxiv.org\/abs\/1901.07291"},{"key":"e_1_3_2_1_19_1","volume-title":"Donghwan Kim, and Sung Ju Hwang.","author":"Lee Dong Bok","year":"2020","unstructured":"Dong Bok Lee, Seanie Lee, Woo Tae Jeong, Donghwan Kim, and Sung Ju Hwang. 2020. Generating diverse and consistent QA pairs from contexts with information-maximizing hierarchical conditional VAEs. arXiv preprint arXiv:2005.13837 (2020)."},{"key":"e_1_3_2_1_20_1","volume-title":"MLQA: Evaluating Cross-lingual Extractive Question Answering. ArXiv","author":"Lewis Patrick","year":"2019","unstructured":"Patrick Lewis, Barlas O?uz, Ruty Rinott, Sebastian Riedel, and Holger Schwenk. 2019. MLQA: Evaluating Cross-lingual Extractive Question Answering. ArXiv, Vol. abs\/1910.07475 (2019). https:\/\/arxiv.org\/abs\/1910.07475"},{"key":"e_1_3_2_1_21_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems Vol. 33 (2020) 9459-9474."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i8.37597"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-industry.108"},{"key":"e_1_3_2_1_24_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74-81. https:\/\/aclanthology.org\/W04-1013"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380270"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.211"},{"key":"e_1_3_2_1_27_1","volume-title":"Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, et al.","author":"Rozi\u00e8re Baptiste","year":"2023","unstructured":"Baptiste Rozi\u00e8re, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, et al., 2023. Code Llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023). https:\/\/arxiv.org\/abs\/2308.12950"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 7106-7126","author":"Sengupta Saptarshi","year":"2025","unstructured":"Saptarshi Sengupta, Wenpeng Yin, Preslav Nakov, Shreya Ghosh, and Suhang Wang. 2025. Exploring language model generalization in low-resource extractive QA. In Proceedings of the 31st International Conference on Computational Linguistics. 7106-7126."},{"key":"e_1_3_2_1_29_1","volume-title":"DRCD: a Chinese Machine Reading Comprehension Dataset. ArXiv","author":"Shao Chih-Chieh","year":"2018","unstructured":"Chih-Chieh Shao, Trois Liu, Yuting Lai, Yiying Tseng, and Sam Tsai. 2018. DRCD: a Chinese Machine Reading Comprehension Dataset. ArXiv, Vol. abs\/1806.00920 (2018). https:\/\/api.semanticscholar.org\/CorpusID:46932369"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.391"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.eacl-long.91"},{"key":"e_1_3_2_1_32_1","volume-title":"Question answering and question generation as dual tasks. arXiv preprint arXiv:1706.02027","author":"Tang Duyu","year":"2017","unstructured":"Duyu Tang, Nan Duan, Tao Qin, Zhao Yan, and Ming Zhou. 2017. Question answering and question generation as dual tasks. arXiv preprint arXiv:1706.02027 (2017)."},{"key":"e_1_3_2_1_33_1","volume-title":"Hashimoto","author":"Taori Rohan","year":"2023","unstructured":"Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_1_34_1","volume-title":"Representing Numbers in NLP: a Survey and a Vision. ArXiv","author":"Thawani Avijit","year":"2021","unstructured":"Avijit Thawani, Jay Pujara, Pedro A. Szekely, and Filip Ilievski. 2021. Representing Numbers in NLP: a Survey and a Vision. ArXiv, Vol. abs\/2103.13136 (2021). https:\/\/arxiv.org\/abs\/2103.13136"},{"key":"e_1_3_2_1_35_1","unstructured":"Hugo Touvron Louis Martin Kevin R. Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Daniel M. Bikel Lukas Blecher Cristian Cant\u00f3n Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony S. Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel M. Kloumann A. V. Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith R. Subramanian Xia Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zhengxu Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. ArXiv Vol. abs\/2307.09288 (2023). https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_1_36_1","volume-title":"Probing Pretrained Language Models for Lexical Semantics. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:222290596","author":"Vulic Ivan","year":"2020","unstructured":"Ivan Vulic, E. Ponti, Robert Litschko, Goran Glavas, and Anna Korhonen. 2020. Probing Pretrained Language Models for Lexical Semantics. In Conference on Empirical Methods in Natural Language Processing. https:\/\/api.semanticscholar.org\/CorpusID:222290596"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i19.38619"},{"key":"e_1_3_2_1_38_1","volume-title":"A joint model for question answering and question generation. arXiv preprint arXiv:1706.01450","author":"Wang Tong","year":"2017","unstructured":"Tong Wang, Xingdi Yuan, and Adam Trischler. 2017. A joint model for question answering and question generation. arXiv preprint arXiv:1706.01450 (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.63317\/44783esymd2m"},{"key":"e_1_3_2_1_40_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang Guanting Dong Haoran Wei Huan Lin Jialong Tang Jialin Wang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Ma Jin Xu Jingren Zhou Jinze Bai Jinzheng He Junyang Lin Kai Dang Keming Lu Keqin Chen Kexin Yang Mei Li Mingfeng Xue Na Ni Pei Zhang Peng Wang Ru Peng Rui Men Ruize Gao Runji Lin Shijie Wang Shuai Bai Sinan Tan Tianhang Zhu Tianhao Li Tianyu Liu Wenbin Ge Xiaodong Deng Xiaohuan Zhou Xingzhang Ren Xinyu Zhang Xipin Wei Xuancheng Ren Yang Fan Yang Yao Yichang Zhang Yu Wan Yunfei Chu Yuqiong Liu Zeyu Cui Zhenru Zhang and Zhihao Fan. 2024. Qwen2 Technical Report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Shirui Pan, Tianyue Wang, and Haishuai Wang.","author":"Yu Jiajun","year":"2025","unstructured":"Jiajun Yu, Yizhen Zheng, Huan Yee Koh, Shirui Pan, Tianyue Wang, and Haishuai Wang. 2025. Collaborative expert llms guided multi-objective molecular optimization. arXiv preprint arXiv:2503.03503 (2025)."},{"key":"e_1_3_2_1_42_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."},{"key":"e_1_3_2_1_43_1","volume-title":"Systematic discovery of single-cell protein networks in cancer with Shusi. bioRxiv","author":"Zhang Tianyun","year":"2025","unstructured":"Tianyun Zhang, Jiajun Yu, Shang Lou, Yaozhen Liang, Yue Liang, Zhekai Li, Haishuai Wang, Shanshan Pei, and Ning Shen. 2025. Systematic discovery of single-cell protein networks in cancer with Shusi. bioRxiv (2025), 2025-04."}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:22:22Z","timestamp":1784136142000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":43,"alternative-id":["10.1145\/3805712.3808516","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808516","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}