{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:03:13Z","timestamp":1783526593382,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"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":[[2024,11,14]]},"DOI":"10.1145\/3677052.3698686","type":"proceedings-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T06:38:06Z","timestamp":1731566286000},"page":"530-537","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Enhancing Financial Question Answering with a Multi-Agent Reflection Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5163-2541","authenticated-orcid":false,"given":"Sorouralsadat","family":"Fatemi","sequence":"first","affiliation":[{"name":"University of Illinois at Chicago, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3665-1238","authenticated-orcid":false,"given":"Yuheng","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Illinois at Chicago, US"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712","author":"Bubeck S\u00e9bastien","year":"2023","unstructured":"S\u00e9bastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin\u00a0Tat Lee, Yuanzhi Li, Scott Lundberg, 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Reconcile: Round-table conference improves reasoning via consensus among diverse llms. arXiv preprint arXiv:2309","author":"Chih-Yao Chen Justin","year":"2023","unstructured":"Justin Chih-Yao Chen, Swarnadeep Saha, and Mohit Bansal. 2023. Reconcile: Round-table conference improves reasoning via consensus among diverse llms. arXiv preprint arXiv:2309.13007 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Finqa: A dataset of numerical reasoning over financial data. arXiv preprint arXiv:2109.00122","author":"Chen Zhiyu","year":"2021","unstructured":"Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan Routledge, 2021. Finqa: A dataset of numerical reasoning over financial data. arXiv preprint arXiv:2109.00122 (2021)."},{"key":"e_1_3_2_1_4_1","volume-title":"Convfinqa: Exploring the chain of numerical reasoning in conversational finance question answering. arXiv preprint arXiv:2210.03849","author":"Chen Zhiyu","year":"2022","unstructured":"Zhiyu Chen, Shiyang Li, Charese Smiley, Zhiqiang Ma, Sameena Shah, and William\u00a0Yang Wang. 2022. Convfinqa: Exploring the chain of numerical reasoning in conversational finance question answering. arXiv preprint arXiv:2210.03849 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168","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, 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_1_6_1","volume-title":"Improving factuality and reasoning in language models through multiagent debate. arXiv preprint arXiv:2305.14325","author":"Du Yilun","year":"2023","unstructured":"Yilun Du, Shuang Li, Antonio Torralba, Joshua\u00a0B Tenenbaum, and Igor Mordatch. 2023. Improving factuality and reasoning in language models through multiagent debate. arXiv preprint arXiv:2305.14325 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Critic: Large language models can self-correct with tool-interactive critiquing. arXiv preprint arXiv:2305.11738","author":"Gou Zhibin","year":"2023","unstructured":"Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, and Weizhu Chen. 2023. Critic: Large language models can self-correct with tool-interactive critiquing. arXiv preprint arXiv:2305.11738 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Reasoning with language model is planning with world model. arXiv preprint arXiv:2305.14992","author":"Hao Shibo","year":"2023","unstructured":"Shibo Hao, Yi Gu, Haodi Ma, Joshua\u00a0Jiahua Hong, Zhen Wang, Daisy\u00a0Zhe Wang, and Zhiting Hu. 2023. Reasoning with language model is planning with world model. arXiv preprint arXiv:2305.14992 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning. arXiv preprint arXiv:2406.06469","author":"Kim Joongwon","year":"2024","unstructured":"Joongwon Kim, Bhargavi Paranjape, Tushar Khot, and Hannaneh Hajishirzi. 2024. Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning. arXiv preprint arXiv:2406.06469 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Answering numerical reasoning questions in table-text hybrid contents with graph-based encoder and tree-based decoder. arXiv preprint arXiv:2209.07692","author":"Lei Fangyu","year":"2022","unstructured":"Fangyu Lei, Shizhu He, Xiang Li, Jun Zhao, and Kang Liu. 2022. Answering numerical reasoning questions in table-text hybrid contents with graph-based encoder and tree-based decoder. arXiv preprint arXiv:2209.07692 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate. arXiv preprint arXiv:2407.20505","author":"Lin Zheng","year":"2024","unstructured":"Zheng Lin, Zhenxing Niu, Zhibin Wang, and Yinghui Xu. 2024. Interpreting and Mitigating Hallucination in MLLMs through Multi-agent Debate. arXiv preprint arXiv:2407.20505 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Society of mind","author":"Minsky Marvin","unstructured":"Marvin Minsky. 1988. Society of mind. Simon and Schuster."},{"key":"e_1_3_2_1_13_1","unstructured":"OpenAI. 2022. ChatGPT. https:\/\/openai.com\/blog\/chatgpt Accessed: [Date you accessed the website]."},{"key":"e_1_3_2_1_14_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. Technical Report."},{"key":"e_1_3_2_1_15_1","volume-title":"Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789","author":"Qin Yujia","year":"2023","unstructured":"Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, 2023. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"Self-Reflection in LLM Agents: Effects on Problem-Solving Performance. arXiv preprint arXiv:2405.06682","author":"Renze Matthew","year":"2024","unstructured":"Matthew Renze and Erhan Guven. 2024. Self-Reflection in LLM Agents: Effects on Problem-Solving Performance. arXiv preprint arXiv:2405.06682 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Auto-GPT: an autonomous GPT-4 experiment","author":"Toran\u00a0Bruce","year":"2023","unstructured":"Toran\u00a0Bruce Richards 2023. Auto-GPT: an autonomous GPT-4 experiment (2023). URL https:\/\/github. com\/Significant-Gravitas\/Auto-GPT.[Software] (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Towards faithful and robust llm specialists for evidence-based question-answering. arXiv preprint arXiv:2402.08277","author":"Schimanski Tobias","year":"2024","unstructured":"Tobias Schimanski, Jingwei Ni, Mathias Kraus, Elliott Ash, and Markus Leippold. 2024. Towards faithful and robust llm specialists for evidence-based question-answering. arXiv preprint arXiv:2402.08277 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems 36","author":"Shinn Noah","year":"2024","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2024. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155","author":"Wu Qingyun","year":"2023","unstructured":"Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Designing Heterogeneous LLM Agents for Financial Sentiment Analysis. arXiv preprint arXiv:2401.05799","author":"Xing Frank","year":"2024","unstructured":"Frank Xing. 2024. Designing Heterogeneous LLM Agents for Financial Sentiment Analysis. arXiv preprint arXiv:2401.05799 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Are large language models really good logical reasoners? a comprehensive evaluation from deductive, inductive and abductive views. arXiv preprint arXiv:2306.09841","author":"Xu Fangzhi","year":"2023","unstructured":"Fangzhi Xu, Qika Lin, Jiawei Han, Tianzhe Zhao, Jun Liu, and Erik Cambria. 2023. Are large language models really good logical reasoners? a comprehensive evaluation from deductive, inductive and abductive views. arXiv preprint arXiv:2306.09841 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)."},{"key":"e_1_3_2_1_25_1","volume-title":"A survey of large language models. arXiv preprint arXiv:2303.18223","author":"Zhao Wayne\u00a0Xin","year":"2023","unstructured":"Wayne\u00a0Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Unirpg: Unified discrete reasoning over table and text as program generation. arXiv preprint arXiv:2210.08249","author":"Zhou Yongwei","year":"2022","unstructured":"Yongwei Zhou, Junwei Bao, Chaoqun Duan, Youzheng Wu, Xiaodong He, and Tiejun Zhao. 2022. Unirpg: Unified discrete reasoning over table and text as program generation. arXiv preprint arXiv:2210.08249 (2022)."},{"key":"e_1_3_2_1_27_1","volume-title":"TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance. arXiv preprint arXiv:2105.07624","author":"Zhu Fengbin","year":"2021","unstructured":"Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, and Tat-Seng Chua. 2021. TAT-QA: A question answering benchmark on a hybrid of tabular and textual content in finance. arXiv preprint arXiv:2105.07624 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587598"},{"key":"e_1_3_2_1_29_1","volume-title":"Tat-llm: A specialized language model for discrete reasoning over tabular and textual data. arXiv preprint arXiv:2401.13223","author":"Zhu Fengbin","year":"2024","unstructured":"Fengbin Zhu, Ziyang Liu, Fuli Feng, Chao Wang, Moxin Li, and Tat-Seng Chua. 2024. Tat-llm: A specialized language model for discrete reasoning over tabular and textual data. arXiv preprint arXiv:2401.13223 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Solving math word problems via cooperative reasoning induced language models. arXiv preprint arXiv:2210.16257","author":"Zhu Xinyu","year":"2022","unstructured":"Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, Ruyi Gan, Jiaxing Zhang, and Yujiu Yang. 2022. Solving math word problems via cooperative reasoning induced language models. arXiv preprint arXiv:2210.16257 (2022)."},{"key":"e_1_3_2_1_31_1","volume-title":"Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering. arXiv preprint arXiv:2402.14320","author":"Zong Chang","year":"2024","unstructured":"Chang Zong, Yuchen Yan, Weiming Lu, Eliot Huang, Jian Shao, and Yueting Zhuang. 2024. Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering. arXiv preprint arXiv:2402.14320 (2024)."}],"event":{"name":"ICAIF '24: 5th ACM International Conference on AI in Finance","location":"Brooklyn NY USA","acronym":"ICAIF '24"},"container-title":["Proceedings of the 5th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698686","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677052.3698686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:09:41Z","timestamp":1755882581000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677052.3698686"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":31,"alternative-id":["10.1145\/3677052.3698686","10.1145\/3677052"],"URL":"https:\/\/doi.org\/10.1145\/3677052.3698686","relation":{},"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"2024-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}