{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:35:52Z","timestamp":1780637752935,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T00:00:00Z","timestamp":1700870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,27]]},"DOI":"10.1145\/3604237.3626869","type":"proceedings-article","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T18:09:47Z","timestamp":1700935787000},"page":"374-382","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":227,"title":["Large Language Models in Finance: A Survey"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7740-2484","authenticated-orcid":false,"given":"Yinheng","family":"Li","sequence":"first","affiliation":[{"name":"Columbia University, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7620-5398","authenticated-orcid":false,"given":"Shaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Columbia University, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7961-0036","authenticated-orcid":false,"given":"Han","family":"Ding","sequence":"additional","affiliation":[{"name":"Columbia University, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2981-2106","authenticated-orcid":false,"given":"Hang","family":"Chen","sequence":"additional","affiliation":[{"name":"New York University, US"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,11,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2023. Auto-GPT: An Autonomous GPT-4 Experiment. https:\/\/github.com\/Significant-Gravitas\/Auto-GPT."},{"key":"e_1_3_2_1_2_1","unstructured":"2023. Chatbots in consumer finance. https:\/\/www.consumerfinance.gov\/data-research\/research-reports\/chatbots-in-consumer-finance\/chatbots-in-consumer-finance\/"},{"key":"e_1_3_2_1_3_1","first-page":"1","article-title":"Markov models applications in natural language processing: a survey","volume":"2","author":"Almutiri Talal","year":"2022","unstructured":"Talal Almutiri and Farrukh Nadeem. 2022. Markov models applications in natural language processing: a survey. Int. J. Inf. Technol. Comput. Sci 2 (2022), 1\u201316.","journal-title":"Int. J. Inf. Technol. Comput. Sci"},{"key":"e_1_3_2_1_4_1","unstructured":"Harrison Chase. 2022. LangChain. https:\/\/github.com\/hwchase17\/langchain"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2011.10.030"},{"key":"e_1_3_2_1_6_1","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/","author":"\u00a0al Wei-Lin","year":"2023","unstructured":"Wei-Lin et\u00a0al. Chiang. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"e_1_3_2_1_7_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv:1810.04805\u00a0[cs.CL]","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv:1810.04805\u00a0[cs.CL]"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_1_9_1","unstructured":"Aakanksha\u00a0Chowdhery et al.2022. PaLM: Scaling Language Modeling with Pathways. arxiv:2204.02311\u00a0[cs.CL]"},{"key":"e_1_3_2_1_10_1","unstructured":"Amir\u00a0Gholami et al.2021. A Survey of Quantization Methods for Efficient Neural Network Inference. arxiv:2103.13630\u00a0[cs.CV]"},{"key":"e_1_3_2_1_11_1","unstructured":"Ashish\u00a0Vaswani et al.2017. Attention Is All You Need. arxiv:1706.03762\u00a0[cs.CL]"},{"key":"e_1_3_2_1_12_1","volume-title":"The Eleventh International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=-Aw0rrrPUF","author":"Aohan\u00a0Zeng","unstructured":"Aohan\u00a0Zeng et al.2023. GLM-130B: An Open Bilingual Pre-trained Model. In The Eleventh International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=-Aw0rrrPUF"},{"key":"e_1_3_2_1_13_1","volume-title":"2000. A neural probabilistic language model. Advances in neural information processing systems 13","author":"Bengio","year":"2000","unstructured":"Bengio et al.2000. A neural probabilistic language model. Advances in neural information processing systems 13 (2000)."},{"key":"e_1_3_2_1_14_1","unstructured":"BigScience\u00a0Workshop et al.2023. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model. arxiv:2211.05100\u00a0[cs.CL]"},{"key":"e_1_3_2_1_15_1","unstructured":"Colin\u00a0Raffel et al.2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. arxiv:1910.10683\u00a0[cs.LG]"},{"key":"e_1_3_2_1_16_1","unstructured":"Dhiraj\u00a0Kalamkaret et al.2019. A Study of BFLOAT16 for Deep Learning Training. arxiv:1905.12322\u00a0[cs.LG]"},{"key":"e_1_3_2_1_17_1","unstructured":"Dakuan\u00a0Lu et al.2023. BBT-Fin: Comprehensive Construction of Chinese Financial Domain Pre-trained Language Model Corpus and Benchmark. arxiv:2302.09432\u00a0[cs.CL]"},{"key":"e_1_3_2_1_18_1","unstructured":"Edward J.\u00a0Hu et al.2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv:2106.09685\u00a0[cs.CL]"},{"key":"e_1_3_2_1_19_1","unstructured":"Hyung Won\u00a0Chung et al.2022. Scaling Instruction-Finetuned Language Models. arxiv:2210.11416\u00a0[cs.LG]"},{"key":"e_1_3_2_1_20_1","volume-title":"2022. Chain of Thought Prompting Elicits Reasoning in Large Language Models. CoRR abs\/2201.11903","author":"Jason\u00a0Wei","year":"2022","unstructured":"Jason\u00a0Wei et al.2022. Chain of Thought Prompting Elicits Reasoning in Large Language Models. CoRR abs\/2201.11903 (2022). arXiv:2201.11903https:\/\/arxiv.org\/abs\/2201.11903"},{"key":"e_1_3_2_1_21_1","unstructured":"Jason\u00a0Wei et al.2022. Emergent Abilities of Large Language Models. arxiv:2206.07682\u00a0[cs.CL]"},{"key":"e_1_3_2_1_22_1","unstructured":"Jingfeng\u00a0Yang et al.2023. Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond. arxiv:2304.13712\u00a0[cs.CL]"},{"key":"e_1_3_2_1_23_1","unstructured":"Kyunghyun\u00a0Cho et al.2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. arxiv:1406.1078\u00a0[cs.CL]"},{"key":"e_1_3_2_1_24_1","unstructured":"Long\u00a0Ouyang et al.2022. Training language models to follow instructions with human feedback. arxiv:2203.02155\u00a0[cs.CL]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494388"},{"key":"e_1_3_2_1_26_1","unstructured":"Patrick\u00a0Lewis et al.2021. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arxiv:2005.11401\u00a0[cs.CL]"},{"key":"e_1_3_2_1_27_1","unstructured":"Percy\u00a0Liang et al.2022. Holistic Evaluation of Language Models. arxiv:2211.09110\u00a0[cs.CL]"},{"key":"e_1_3_2_1_28_1","unstructured":"Qingsong\u00a0Wen et al.2023. Transformers in Time Series: A Survey. arxiv:2202.07125\u00a0[cs.LG]"},{"key":"e_1_3_2_1_29_1","unstructured":"Qianqian\u00a0Xie et al.2023. PIXIU: A Large Language Model Instruction Data and Evaluation Benchmark for Finance. arxiv:2306.05443\u00a0[cs.CL]"},{"key":"e_1_3_2_1_30_1","unstructured":"Shijie\u00a0Wu et al.2023. BloombergGPT: A Large Language Model for Finance. arxiv:2303.17564\u00a0[cs.LG]"},{"key":"e_1_3_2_1_31_1","unstructured":"Shunyu\u00a0Yao et al.2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. arxiv:2305.10601\u00a0[cs.CL]"},{"key":"e_1_3_2_1_32_1","unstructured":"Susan\u00a0Zhang et al.2022. OPT: Open Pre-trained Transformer Language Models. arxiv:2205.01068\u00a0[cs.CL]"},{"key":"e_1_3_2_1_33_1","unstructured":"Tom B.\u00a0Brown et al.2020. Language Models are Few-Shot Learners. arxiv:2005.14165\u00a0[cs.CL]"},{"key":"e_1_3_2_1_34_1","volume-title":"2020. Language Models are Few-Shot Learners. CoRR abs\/2005.14165","author":"Brown Tom","year":"2020","unstructured":"Tom B.\u00a0Brown et al.2020. Language Models are Few-Shot Learners. CoRR abs\/2005.14165 (2020). arXiv:2005.14165https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Wenxuan\u00a0Zhang et al.2023. Sentiment Analysis in the Era of Large Language Models: A Reality Check. arxiv:2305.15005\u00a0[cs.CL]","DOI":"10.18653\/v1\/2024.findings-naacl.246"},{"key":"e_1_3_2_1_36_1","unstructured":"Yaqing\u00a0Wang et al.2020. Generalizing from a Few Examples: A Survey on Few-Shot Learning. arxiv:1904.05046\u00a0[cs.LG]"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/math10132156"},{"key":"e_1_3_2_1_38_1","unstructured":"Peter Foy. 2023. GPT-4 for Financial Statements: Building an AI Analyst. MLQ AI. https:\/\/www.mlq.ai\/gpt-4-financial-statements-ai-analyst\/"},{"key":"e_1_3_2_1_39_1","unstructured":"Xinyang Geng and Hao Liu. 2023. OpenLLaMA: An Open Reproduction of LLaMA. https:\/\/github.com\/openlm-research\/open_llama"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbef.2021.100577"},{"key":"e_1_3_2_1_41_1","unstructured":"Alex Graves. 2014. Generating Sequences With Recurrent Neural Networks. arxiv:1308.0850\u00a0[cs.NE]"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40854-020-00205-1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(03)00372-2"},{"key":"e_1_3_2_1_44_1","volume-title":"International Conference Recent Advances in Natural Language Processing.","author":"Li Yinheng","year":"2023","unstructured":"Yinheng Li. 2023. A Practical Survey on Zero-shot Prompt Design for In-context Learning. International Conference Recent Advances in Natural Language Processing."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.12.002"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036322"},{"key":"e_1_3_2_1_47_1","unstructured":"Microsoft. 2023. Semantic Kernel. https:\/\/github.com\/microsoft\/semantic-kernel."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.03.055"},{"key":"e_1_3_2_1_49_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arxiv:2303.08774\u00a0[cs.CL]"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Ahmet\u00a0Murat Ozbayoglu Mehmet\u00a0Ugur Gudelek and Omer\u00a0Berat Sezer. 2020. Deep Learning for Financial Applications : A Survey. arxiv:2002.05786\u00a0[q-fin.ST]","DOI":"10.1016\/j.asoc.2020.106384"},{"key":"e_1_3_2_1_51_1","unstructured":"Igor Radovanovic. 2023. Auto-GPT for finance - an exploratory guide - algotrading101 blog. https:\/\/algotrading101.com\/learn\/auto-gpt-finance-guide\/"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIEDS.2018.8374722"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.09.031"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","unstructured":"Ashish et\u00a0al. Shah. 2020. FinAID A Financial Advisor Application using AI. 2282\u20132286\u00a0pages. https:\/\/doi.org\/10.35940\/ijrte.a2951.059120","DOI":"10.35940\/ijrte.a2951.059120"},{"key":"e_1_3_2_1_55_1","unstructured":"Hugh Son. 2023. JPMorgan is developing a CHATGPT-like A.I. service that gives investment advice. https:\/\/www.cnbc.com\/2023\/05\/25\/jpmorgan-develops-ai-investment-advisor.html"},{"key":"e_1_3_2_1_56_1","unstructured":"Alex Tamkin Miles Brundage Jack Clark and Deep Ganguli. 2021. Understanding the Capabilities Limitations and Societal Impact of Large Language Models. arxiv:2102.02503\u00a0[cs.CL]"},{"key":"e_1_3_2_1_57_1","volume-title":"Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca.","author":"Taori Rohan","year":"2023","unstructured":"Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori\u00a0B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_1_58_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv:2302.13971\u00a0[cs.CL]"},{"key":"e_1_3_2_1_59_1","unstructured":"Junhao Wang Yinheng Li and Yijie Cao. 2019. Dynamic Portfolio Management with Reinforcement Learning. arxiv:1911.11880\u00a0[q-fin.PM]"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0305-0548(99)00149-5"},{"key":"e_1_3_2_1_61_1","unstructured":"Pedram\u00a0Babaei William\u00a0Todt Ramtin\u00a0Babaei. 2023. Fin-LLAMA: Efficient Finetuning of Quantized LLMs for Finance. https:\/\/github.com\/Bavest\/fin-llama."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-017-9588-9"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Hongyang Yang Xiao-Yang Liu and Christina\u00a0Dan Wang. 2023. FinGPT: Open-Source Financial Large Language Models. arxiv:2306.06031\u00a0[q-fin.ST]","DOI":"10.2139\/ssrn.4489826"},{"key":"e_1_3_2_1_64_1","unstructured":"YangMu Yu. 2023. Cornucopia-LLaMA-Fin-Chinese. https:\/\/github.com\/jerry1993-tech\/Cornucopia-LLaMA-Fin-Chinese."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Boyu Zhang Hongyang Yang and Xiao-Yang Liu. 2023. Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models. arxiv:2306.12659\u00a0[cs.CL]","DOI":"10.2139\/ssrn.4489831"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","unstructured":"Xuanyu Zhang Qing Yang and Dongliang Xu. 2023. XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters. arxiv:2305.12002\u00a0[cs.CL]","DOI":"10.1145\/3583780.3615285"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.3905\/jfds.2020.1.042"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Ekaterina Zolotareva. 2021. Aiding Long-Term Investment Decisions with XGBoost Machine Learning Model. arxiv:2104.09341\u00a0[q-fin.CP]","DOI":"10.1007\/978-3-030-87897-9_37"}],"event":{"name":"ICAIF '23: 4th ACM International Conference on AI in Finance","location":"Brooklyn NY USA","acronym":"ICAIF '23"},"container-title":["4th ACM International Conference on AI in Finance"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604237.3626869","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604237.3626869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:38:59Z","timestamp":1755884339000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604237.3626869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,25]]},"references-count":68,"alternative-id":["10.1145\/3604237.3626869","10.1145\/3604237"],"URL":"https:\/\/doi.org\/10.1145\/3604237.3626869","relation":{},"subject":[],"published":{"date-parts":[[2023,11,25]]},"assertion":[{"value":"2023-11-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}