{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:16:27Z","timestamp":1785856587757,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:00:00Z","timestamp":1698192000000},"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":[[2023,10,25]]},"DOI":"10.1145\/3639856.3639895","type":"proceedings-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T11:49:10Z","timestamp":1715946550000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Towards reducing hallucination in extracting information from financial reports using Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3076-9539","authenticated-orcid":false,"given":"Bhaskarjit","family":"Sarmah","sequence":"first","affiliation":[{"name":"BlackRock, IN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1040-9032","authenticated-orcid":false,"given":"Dhagash","family":"Mehta","sequence":"additional","affiliation":[{"name":"BlackRock, Inc., US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8005-3207","authenticated-orcid":false,"given":"Stefano","family":"Pasquali","sequence":"additional","affiliation":[{"name":"BlackRock, Inc., USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9402-6325","authenticated-orcid":false,"given":"Tianjie","family":"Zhu","sequence":"additional","affiliation":[{"name":"BlackRock, Inc., USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Palm 2 technical report. arXiv preprint arXiv:2305.10403","author":"Anil Rohan","year":"2023","unstructured":"Rohan Anil, Andrew\u00a0M Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, 2023. Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPIRE.2000.878178"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. PMLR, 2397\u20132430","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin\u00a0Gregory Anthony, Herbie Bradley, Kyle O\u2019Brien, Eric Hallahan, Mohammad\u00a0Aflah Khan, Shivanshu Purohit, USVSN\u00a0Sai Prashanth, Edward Raff, 2023. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning. PMLR, 2397\u20132430."},{"key":"e_1_3_2_1_4_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_1_5_1","volume-title":"Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416","author":"Chung Hyung\u00a0Won","year":"2022","unstructured":"Hyung\u00a0Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"Intelligent Document Processing\u2013Methods and Tools in the real world. arXiv preprint arXiv:2112.14070","author":"Cutting A","year":"2021","unstructured":"Graham\u00a0A Cutting and Anne-Fran\u00e7oise Cutting-Decelle. 2021. Intelligent Document Processing\u2013Methods and Tools in the real world. arXiv preprint arXiv:2112.14070 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"TIPSTER TEXT PROGRAM PHASE III: Proceedings of a Workshop held at Baltimore","author":"Goldstein Jade","year":"1998","unstructured":"Jade Goldstein and Jaime\u00a0G Carbonell. 1998. Summarization:(1) using MMR for diversity-based reranking and (2) evaluating summaries. In TIPSTER TEXT PROGRAM PHASE III: Proceedings of a Workshop held at Baltimore, Maryland, October 13-15, 1998. 181\u2013195."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2021.116601"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1989.10478785"},{"key":"e_1_3_2_1_11_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020), 9459\u20139474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","volume-title":"RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit. arXiv preprint arXiv:2306.05212","author":"Liu Jiongnan","year":"2023","unstructured":"Jiongnan Liu, Jiajie Jin, Zihan Wang, Jiehan Cheng, Zhicheng Dou, and Ji-Rong Wen. 2023. RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit. arXiv preprint arXiv:2306.05212 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Graph convolution for multimodal information extraction from visually rich documents. arXiv preprint arXiv:1903.11279","author":"Liu Xiaojing","year":"2019","unstructured":"Xiaojing Liu, Feiyu Gao, Qiong Zhang, and Huasha Zhao. 2019. Graph convolution for multimodal information extraction from visually rich documents. arXiv preprint arXiv:1903.11279 (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"Crosslingual generalization through multitask finetuning. arXiv preprint arXiv:2211.01786","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven\u00a0Le Scao, M\u00a0Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, 2022. Crosslingual generalization through multitask finetuning. arXiv preprint arXiv:2211.01786 (2022)."},{"key":"e_1_3_2_1_15_1","volume-title":"Paradigm Shift in Sustainability Disclosure Analysis: Empowering Stakeholders with CHATREPORT, a Language Model-Based Tool. arXiv preprint arXiv:2306.15518","author":"Ni Jingwei","year":"2023","unstructured":"Jingwei Ni, Julia Bingler, Chiara Colesanti-Senni, Mathias Kraus, Glen Gostlow, Tobias Schimanski, Dominik Stammbach, Saeid\u00a0Ashraf Vaghefi, Qian Wang, Nicolas Webersinke, 2023. Paradigm Shift in Sustainability Disclosure Analysis: Empowering Stakeholders with CHATREPORT, a Language Model-Based Tool. arXiv preprint arXiv:2306.15518 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Abstractive information extraction from scanned invoices (AIESI) using end-to-end sequential approach. arXiv preprint arXiv:2009.05728","author":"Patel Shreeshiv","year":"2020","unstructured":"Shreeshiv Patel and Dvijesh Bhatt. 2020. Abstractive information extraction from scanned invoices (AIESI) using end-to-end sequential approach. arXiv preprint arXiv:2009.05728 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Graphie: A graph-based framework for information extraction. arXiv preprint arXiv:1810.13083","author":"Qian Yujie","year":"2018","unstructured":"Yujie Qian, Enrico Santus, Zhijing Jin, Jiang Guo, and Regina Barzilay. 2018. Graphie: A graph-based framework for information extraction. arXiv preprint arXiv:1810.13083 (2018)."},{"key":"e_1_3_2_1_18_1","first-page":"10","article-title":"A rule-based system to extract financial information","volume":"52","author":"Sheikh Mahmudul","year":"2012","unstructured":"Mahmudul Sheikh and Sumali Conlon. 2012. A rule-based system to extract financial information. Journal of Computer Information Systems 52, 4 (2012), 10\u201319.","journal-title":"Journal of Computer Information Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"Docile benchmark for document information localization and extraction. arXiv preprint arXiv:2302.05658","author":"\u0160imsa \u0160t\u011bp\u00e1n","year":"2023","unstructured":"\u0160t\u011bp\u00e1n \u0160imsa, Milan \u0160ulc, Michal U\u0159i\u010d\u00e1\u0159, Yash Patel, Ahmed Hamdi, Mat\u011bj Koci\u00e1n, Maty\u00e1\u0161 Skalick\u1ef3, Ji\u0159\u00ed Matas, Antoine Doucet, Micka\u00ebl Coustaty, 2023. Docile benchmark for document information localization and extraction. arXiv preprint arXiv:2302.05658 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_21_1","unstructured":"William\u00a0E Winkler. 1990. String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage. (1990)."},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates","author":"Yuan Weizhe","year":"2021","unstructured":"Weizhe Yuan, Graham Neubig, and Pengfei Liu. 2021. BARTScore: Evaluating Generated Text as Text Generation. In Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates, Inc., 27263\u201327277. https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/e4d2b6e6fdeca3e60e0f1a62fee3d9dd-Paper.pdf"},{"key":"e_1_3_2_1_23_1","volume-title":"Leveraging LLMs for KPIs Retrieval from Hybrid Long-Document: A Comprehensive Framework and Dataset. arXiv preprint arXiv:2305.16344","author":"Yue Chongjian","year":"2023","unstructured":"Chongjian Yue, Xinrun Xu, Xiaojun Ma, Lun Du, Hengyu Liu, Zhiming Ding, Yanbing Jiang, Shi Han, and Dongmei Zhang. 2023. Leveraging LLMs for KPIs Retrieval from Hybrid Long-Document: A Comprehensive Framework and Dataset. arXiv preprint arXiv:2305.16344 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr","author":"Tianyi","year":"2020","unstructured":"Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian\u00a0Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr"},{"key":"e_1_3_2_1_25_1","volume-title":"ToolQA: A Dataset for LLM Question Answering with External Tools. arXiv preprint arXiv:2306.13304","author":"Zhuang Yuchen","year":"2023","unstructured":"Yuchen Zhuang, Yue Yu, Kuan Wang, Haotian Sun, and Chao Zhang. 2023. ToolQA: A Dataset for LLM Question Answering with External Tools. arXiv preprint arXiv:2306.13304 (2023)."}],"event":{"name":"AIMLSystems 2023: The Third International Conference on Artificial Intelligence and Machine Learning Systems","location":"Bangalore India","acronym":"AIMLSystems 2023"},"container-title":["Proceedings of the Third International Conference on AI-ML Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639856.3639895","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3639856.3639895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T15:21:51Z","timestamp":1785770511000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639856.3639895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,25]]},"references-count":25,"alternative-id":["10.1145\/3639856.3639895","10.1145\/3639856"],"URL":"https:\/\/doi.org\/10.1145\/3639856.3639895","relation":{},"subject":[],"published":{"date-parts":[[2023,10,25]]},"assertion":[{"value":"2024-05-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}