{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:47:01Z","timestamp":1755794821891,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709400","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:42:22Z","timestamp":1743792142000},"page":"2271-2281","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Multi-Expert Tabular Language Model for Banking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8603-8904","authenticated-orcid":false,"given":"Yue","family":"Guo","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2712-6941","authenticated-orcid":false,"given":"Wentao","family":"Zhang","sequence":"additional","affiliation":[{"name":"WeBank, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4893-2070","authenticated-orcid":false,"given":"Xiaojun","family":"Zhang","sequence":"additional","affiliation":[{"name":"WeBank, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0904-3184","authenticated-orcid":false,"given":"Vincent W.","family":"Zheng","sequence":"additional","affiliation":[{"name":"WeBank, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8863-112X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00544"},{"key":"e_1_3_2_1_2_1","volume-title":"Language Models are Few-Shot Learners. (2020). arxiv","author":"Brown Tom B.","year":"2005","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. (2020). arxiv: 2005.14165 [cs.CL]"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.421"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham Hyung Won Chung Charles Sutton Sebastian Gehrmann Parker Schuh Kensen Shi Sasha Tsvyashchenko Joshua Maynez Abhishek Rao Parker Barnes Yi Tay Noam Shazeer Vinodkumar Prabhakaran Emily Reif Nan Du Ben Hutchinson Reiner Pope James Bradbury Jacob Austin Michael Isard Guy Gur-Ari Pengcheng Yin Toju Duke Anselm Levskaya Sanjay Ghemawat Sunipa Dev Henryk Michalewski Xavier Garcia Vedant Misra Kevin Robinson Liam Fedus Denny Zhou Daphne Ippolito David Luan Hyeontaek Lim Barret Zoph Alexander Spiridonov Ryan Sepassi David Dohan Shivani Agrawal Mark Omernick Andrew M. Dai Thanumalayan Sankaranarayana Pillai Marie Pellat Aitor Lewkowycz Erica Moreira Rewon Child Oleksandr Polozov Katherine Lee Zongwei Zhou Xuezhi Wang Brennan Saeta Mark Diaz Orhan Firat Michele Catasta Jason Wei Kathy Meier-Hellstern Douglas Eck Jeff Dean Slav Petrov and Noah Fiedel. 2022. PaLM: Scaling Language Modeling with Pathways. CoRR Vol. abs\/2204.02311 (2022). hrefhttps:\/\/doi.org\/10.48550\/arXiv.2204.02311doi:nolinkurl10.48550\/arXiv.2204.02311showeprint[arXiv]2204.02311","DOI":"10.48550\/arXiv.2204.02311nolinkurl10.48550\/arXiv.2204.02311showeprint[arXiv]2204.02311"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542700.3542709nolinkurl10.1145\/3542700.3542709"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19--1423nolinkurl10.18653\/v1\/n19--1423"},{"key":"e_1_3_2_1_8_1","volume-title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. CoRR","author":"Fedus William","year":"2021","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2021. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. CoRR, Vol. abs\/2101.03961 (2021). showeprint[arXiv]2101.03961 https:\/\/arxiv.org\/abs\/2101.03961"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.65"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.58nolinkurl10.18653\/V1\/2023.FINDINGS-EMNLP.58"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.58nolinkurl10.18653\/V1\/2024.FINDINGS-ACL.58"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.19032nolinkurl10.48550\/ARXIV.2406.19032showeprint[arXiv]2406.19032"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.407"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.398"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9--15","volume":"2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9--15 June 2019, Long Beach, California, USA (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 2790--2799. http:\/\/proceedings.mlr.press\/v97\/houlsby19a.html"},{"key":"e_1_3_2_1_16_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.270"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6--11 July 2015 (JMLR Workshop and Conference Proceedings","volume":"456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6--11 July 2015 (JMLR Workshop and Conference Proceedings, Vol. 37), Francis R. Bach and David M. Blei (Eds.). JMLR.org, 448--456. http:\/\/proceedings.mlr.press\/v37\/ioffe15.html"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599366"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra Singh Chaplot Diego de Las Casas Emma Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2024. Mixtral of Experts. CoRR Vol. abs\/2401.04088 (2024). hrefhttps:\/\/doi.org\/10.48550\/ARXIV.2401.04088doi:nolinkurl10.48550\/ARXIV.2401.04088showeprint[arXiv]2401.04088","DOI":"10.48550\/ARXIV.2401.04088nolinkurl10.48550\/ARXIV.2401.04088showeprint[arXiv]2401.04088"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/e17--2068nolinkurl10.18653\/v1\/e17--2068"},{"key":"e_1_3_2_1_22_1","volume-title":"Scaling Laws for Neural Language Models. CoRR","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B. Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling Laws for Neural Language Models. CoRR, Vol. abs\/2001.08361 (2020). showeprint[arXiv]2001.08361 https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_2_1_23_1","volume-title":"LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4--9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 3146--3154. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/6449f44a102fde848669bdd9eb6b76fa-Abstract.html"},{"key":"e_1_3_2_1_24_1","volume-title":"Soyeon Caren Han, and Minseok Song","author":"Lee Jean","year":"2024","unstructured":"Jean Lee, Nicholas Stevens, Soyeon Caren Han, and Minseok Song. 2024. A Survey of Large Language Models in Finance (FinLLMs). arxiv: 2402.02315 [cs.CL]"},{"key":"e_1_3_2_1_25_1","volume-title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In 9th International Conference on Learning Representations, ICLR 2021","author":"Lepikhin Dmitry","year":"2021","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2021. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3--7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=qrwe7XHTmYb"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2403.14341nolinkurl10.48550\/ARXIV.2403.14341showeprint[arXiv]2403.14341"},{"key":"e_1_3_2_1_29_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","author":"Liu Qian","year":"2022","unstructured":"Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, and Jian-Guang Lou. 2022. TAPEX: Table Pre-training via Learning a Neural SQL Executor. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=O50443AsCP"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. hrefhttps:\/\/doi.org\/10.48550\/ARXIV.1907.11692doi:nolinkurl10.48550\/ARXIV.1907.11692","DOI":"10.48550\/ARXIV.1907.11692nolinkurl10.48550\/ARXIV.1907.11692"},{"key":"e_1_3_2_1_31_1","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6--9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23062nolinkurl10.1002\/asi.23062"},{"key":"e_1_3_2_1_33_1","unstructured":"OpenAI. 2023a. GPT-4 Technical Report. arxiv: 2303.08774 [cs.CL]"},{"key":"e_1_3_2_1_34_1","unstructured":"OpenAI. 2023b. GPT-4 Technical Report. CoRR Vol. abs\/2303.08774 (2023). hrefhttps:\/\/doi.org\/10.48550\/arXiv.2303.08774doi:nolinkurl10.48550\/arXiv.2303.08774showeprint[arXiv]2303.08774"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/p15--1142nolinkurl10.3115\/v1\/p15--1142"},{"key":"e_1_3_2_1_36_1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res., Vol. 21 (2020), 140:1--140:67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Machine Learning, ICML 2022","volume":"18346","author":"Rajbhandari Samyam","year":"2022","unstructured":"Samyam Rajbhandari, Conglong Li, Zhewei Yao, Minjia Zhang, Reza Yazdani Aminabadi, Ammar Ahmad Awan, Jeff Rasley, and Yuxiong He. 2022. DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale. In International Conference on Machine Learning, ICML 2022, 17--23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 18332--18346. https:\/\/proceedings.mlr.press\/v162\/rajbhandari22a.html"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.368"},{"key":"e_1_3_2_1_39_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc V. Le, Geoffrey E. Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"e_1_3_2_1_40_1","volume-title":"Impact of News on the Commodity Market: Dataset and Results. CoRR","author":"Sinha Ankur","year":"2020","unstructured":"Ankur Sinha and Tanmay Khandait. 2020. Impact of News on the Commodity Market: Dataset and Results. CoRR, Vol. abs\/2009.04202 (2020). showeprint[arXiv]2009.04202 https:\/\/arxiv.org\/abs\/2009.04202"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/3457390.3457391nolinkurl10.14778\/3457390.3457391"},{"key":"e_1_3_2_1_42_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_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.13971nolinkurl10.48550\/ARXIV.2302.13971showeprint[arXiv]2302.13971"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem 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 Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023b. Llama 2: Open Foundation and Fine-Tuned Chat Models. CoRR Vol. abs\/2307.09288 (2023). hrefhttps:\/\/doi.org\/10.48550\/arXiv.2307.09288doi:nolinkurl10.48550\/arXiv.2307.09288showeprint[arXiv]2307.09288","DOI":"10.48550\/arXiv.2307.09288nolinkurl10.48550\/arXiv.2307.09288showeprint[arXiv]2307.09288"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem 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 Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aur\u00e9lien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023c. Llama 2: Open Foundation and Fine-Tuned Chat Models. CoRR Vol. abs\/2307.09288 (2023). hrefhttps:\/\/doi.org\/10.48550\/arXiv.2307.09288doi:nolinkurl10.48550\/arXiv.2307.09288showeprint[arXiv]2307.09288","DOI":"10.48550\/arXiv.2307.09288nolinkurl10.48550\/arXiv.2307.09288showeprint[arXiv]2307.09288"},{"key":"e_1_3_2_1_46_1","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022","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. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=gEZrGCozdqR"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.17564nolinkurl10.48550\/arXiv.2303.17564showeprint[arXiv]2303.17564"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2306.05443nolinkurl10.48550\/ARXIV.2306.05443showeprint[arXiv]2306.05443"},{"key":"e_1_3_2_1_49_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 Jianxin Yang 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 Xuejing Liu Yang Fan Yang Yao Yichang Zhang Yu Wan Yunfei Chu Yuqiong Liu Zeyu Cui Zhenru Zhang Zhifang Guo and Zhihao Fan. 2024. Qwen2 Technical Report. arxiv: 2407.10671 [cs.CL] https:\/\/arxiv.org\/abs\/2407.10671"},{"key":"e_1_3_2_1_50_1","volume-title":"FinGPT: Open-Source Financial Large Language Models. FinLLM Symposium at IJCAI 2023","author":"Yang Hongyang","year":"2023","unstructured":"Hongyang Yang, Xiao-Yang Liu, and Christina Dan Wang. 2023a. FinGPT: Open-Source Financial Large Language Models. FinLLM Symposium at IJCAI 2023 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.13064nolinkurl10.48550\/ARXIV.2309.13064showeprint[arXiv]2309.13064"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1425"},{"key":"e_1_3_2_1_54_1","volume-title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. CoRR","author":"Zhong Victor","year":"2017","unstructured":"Victor Zhong, Caiming Xiong, and Richard Socher. 2017. Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning. CoRR, Vol. abs\/1709.00103 (2017). showeprint[arXiv]1709.00103 http:\/\/arxiv.org\/abs\/1709.00103"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709400","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:34:13Z","timestamp":1755358453000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":54,"alternative-id":["10.1145\/3690624.3709400","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709400","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}