{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:36:25Z","timestamp":1763105785987,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770409","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"847-855","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Potential of Tool-Enhanced Small Language Models to Match Large Models in Finance"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2674-0427","authenticated-orcid":false,"given":"Gabriel","family":"Assis","sequence":"first","affiliation":[{"name":"Universidade Federal Fluminense, Niter\u00f3i, Rio de Janeiro, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4404-2437","authenticated-orcid":false,"given":"Ayrton","family":"Surica","sequence":"additional","affiliation":[{"name":"Universidade Federal Fluminense, Niter\u00f3i, Rio de Janeiro, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1703-3988","authenticated-orcid":false,"given":"Pedro","family":"Kroll","sequence":"additional","affiliation":[{"name":"Universidade Federal Fluminense, Niter\u00f3i, Rio de Janeiro, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2666-5794","authenticated-orcid":false,"given":"Carina","family":"Munhoz","sequence":"additional","affiliation":[{"name":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa, S\u00e3o Paulo, S\u00e3o Paulo, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9045-1563","authenticated-orcid":false,"given":"Darian","family":"Rabbani","sequence":"additional","affiliation":[{"name":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa, S\u00e3o Paulo, S\u00e3o Paulo, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0993-784X","authenticated-orcid":false,"given":"Edson","family":"Bollis","sequence":"additional","affiliation":[{"name":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa, S\u00e3o Paulo, S\u00e3o Paulo, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2827-7602","authenticated-orcid":false,"given":"Lucas","family":"Pellicer","sequence":"additional","affiliation":[{"name":"Instituto de Ci\u00eancia e Tecnologia Ita\u00fa, S\u00e3o Paulo, S\u00e3o Paulo, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9089-7303","authenticated-orcid":false,"given":"Aline","family":"Paes","sequence":"additional","affiliation":[{"name":"Universidade Federal Fluminense, Niter\u00f3i, Rio de Janeiro, Brazil"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Alibaba. 2024. QwQ: Reflect Deeply on the Boundaries of the Unknown. https:\/\/qwenlm.github.io\/blog\/qwq-32b-preview\/"},{"key":"e_1_3_3_2_3_2","unstructured":"Alibaba. 2025. Qwen2.5 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2412.15115\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"e_1_3_3_2_4_2","unstructured":"Anthropic. 2024. Introducing Claude 3.5 Sonnet. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet"},{"key":"e_1_3_3_2_5_2","unstructured":"Peter Belcak Greg Heinrich Shizhe Diao Yonggan Fu Xin Dong Saurav Muralidharan Yingyan\u00a0Celine Lin and Pavlo Molchanov. 2025. Small Language Models are the Future of Agentic AI. arxiv:https:\/\/arXiv.org\/abs\/2506.02153\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2506.02153"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.774"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"S.\u00a0A. Budennyy V.\u00a0D. Lazarev N.\u00a0N. Zakharenko A.\u00a0N. Korovin O.\u00a0A. Plosskaya D.\u00a0V. Dimitrov V.\u00a0S. Akhripkin I.\u00a0V. Pavlov I.\u00a0V. Oseledets I.\u00a0S. Barsola I.\u00a0V. Egorov A.\u00a0A. Kosterina and L.\u00a0E. Zhukov. 2023. eco2AI: Carbon Emissions Tracking of Machine Learning Models as the First Step Towards Sustainable AI. Doklady Mathematics (Jan. 2023). 10.1134\/S1064562422060230","DOI":"10.1134\/S1064562422060230"},{"key":"e_1_3_3_2_8_2","unstructured":"Ben Burtenshaw Joffrey Thomas and Thomas Simonini. 2025. The Hugging Face Agents Course. https:\/\/github.com\/huggingface\/agents-course."},{"key":"e_1_3_3_2_9_2","unstructured":"Panagiotis Chatzigiannis Wanyun\u00a0Catherine Gu Srinivasan Raghuraman Peter Rindal and Mahdi Zamani. 2023. Privacy-Enhancing Technologies for Financial Data Sharing. arxiv:https:\/\/arXiv.org\/abs\/2306.10200\u00a0[cs.CR] https:\/\/arxiv.org\/abs\/2306.10200"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.328"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.300"},{"key":"e_1_3_3_2_12_2","unstructured":"Zhiyu Chen Jing Ma Xinlu Zhang Nan Hao An Yan Armineh Nourbakhsh Xianjun Yang Julian McAuley Linda\u00a0Ruth Petzold and William\u00a0Yang Wang. 2024. A Survey on Large Language Models for Critical Societal Domains: Finance Healthcare and Law. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=upAWnMgpnH"},{"key":"e_1_3_3_2_13_2","unstructured":"Cohere. 2024. Introducing Command R7B: Fast and efficient generative AI. https:\/\/cohere.com\/blog\/command-r7b"},{"key":"e_1_3_3_2_14_2","unstructured":"DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2501.12948\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Gunnar Friede Timo Busch and Alexander Bassen. 2015. ESG and financial performance: aggregated evidence from more than 2000 empirical studies. Journal of Sustainable Finance & Investment 5 4 (2015) 210\u2013233. 10.1080\/20430795.2015.1118917","DOI":"10.1080\/20430795.2015.1118917"},{"key":"e_1_3_3_2_16_2","unstructured":"Google. 2025. Gemma 3 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2503.19786\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2503.19786"},{"key":"e_1_3_3_2_17_2","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Killamsetty Krishnateja","year":"2021","unstructured":"Krishnateja Killamsetty, Changbin Li, Chen Zhao, Feng Chen, and Anand Sivasubramaniam. 2021. Gradient Matching based Data Subset Selection for Efficient Deep Learning. In Proceedings of the 38th International Conference on Machine Learning. https:\/\/proceedings.mlr.press\/v139\/killamsetty21a.html"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698675"},{"key":"e_1_3_3_2_19_2","volume-title":"ICLR 2024 Workshop on Large Language Model (LLM) Agents","author":"Li Haohang","year":"2024","unstructured":"Haohang Li, Yangyang Yu, Zhi Chen, Yuechen Jiang, Yang Li, Denghui Zhang, Rong Liu, Jordan\u00a0W. Suchow, and Khaldoun Khashanah. 2024. FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design. In ICLR 2024 Workshop on Large Language Model (LLM) Agents. https:\/\/openreview.net\/forum?id=sstfVOwbiG"},{"key":"e_1_3_3_2_20_2","unstructured":"Tula Masterman Sandi Besen Mason Sawtell and Alex Chao. 2024. The Landscape of Emerging AI Agent Architectures for Reasoning Planning and Tool Calling: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2404.11584\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2404.11584"},{"key":"e_1_3_3_2_21_2","unstructured":"Spencer Mateega Carlos Georgescu and Danny Tang. 2025. FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2501.18062\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2501.18062"},{"key":"e_1_3_3_2_22_2","unstructured":"Meta. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv:https:\/\/arXiv.org\/abs\/2307.09288\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_3_2_23_2","unstructured":"Meta. 2024. The Llama 3 Herd of Models. arxiv:https:\/\/arXiv.org\/abs\/2407.21783\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30574"},{"key":"e_1_3_3_2_25_2","unstructured":"OpenAI. 2024. GPT-4 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2303.08774\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_3_2_26_2","unstructured":"OpenAI. 2024. GPT-4o System Card. arxiv:https:\/\/arXiv.org\/abs\/2410.21276\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_3_2_27_2","unstructured":"OpenAI. 2024. OpenAI o1 System Card. arxiv:https:\/\/arXiv.org\/abs\/2412.16720\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2412.16720"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020755"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-short.42"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698682"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Akchay Srivastava and Atif Memon. 2024. Toward Robust Evaluation: A Comprehensive Taxonomy of Datasets and Metrics for Open Domain Question Answering in the Era of Large Language Models. IEEE Access 12 (2024) 117483\u2013117503. 10.1109\/ACCESS.2024.3446854","DOI":"10.1109\/ACCESS.2024.3446854"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.231"},{"key":"e_1_3_3_2_33_2","unstructured":"Theodore Sumers Shunyu Yao Karthik Narasimhan and Thomas Griffiths. 2024. Cognitive Architectures for Language Agents. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=1i6ZCvflQJ"},{"key":"e_1_3_3_2_34_2","unstructured":"Kimi Team. 2025. Kimi K2: Open Agentic Intelligence. arxiv:https:\/\/arXiv.org\/abs\/2507.20534\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2507.20534"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-short.10"},{"key":"e_1_3_3_2_36_2","unstructured":"Shijie Wu Ozan Irsoy Steven Lu Vadim Dabravolski Mark Dredze Sebastian Gehrmann Prabhanjan Kambadur David Rosenberg and Gideon Mann. 2023. BloombergGPT: A Large Language Model for Finance. arxiv:https:\/\/arXiv.org\/abs\/2303.17564\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2303.17564"},{"key":"e_1_3_3_2_37_2","volume-title":"ICLR 2024 Workshop on Large Language Model (LLM) Agents","author":"Wu Yiran","year":"2024","unstructured":"Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin\u00a0Tat Lee, Richard Peng, Qingyun Wu, and Chi Wang. 2024. MathChat: Converse to Tackle Challenging Math Problems with LLM Agents. In ICLR 2024 Workshop on Large Language Model (LLM) Agents. https:\/\/openreview.net\/forum?id=S7vIB7OGQe"},{"key":"e_1_3_3_2_38_2","first-page":"1","volume-title":"Proceedings of the Eighth Financial Technology and Natural Language Processing and the 1st Agent AI for Scenario Planning","author":"Xia Lei","year":"2024","unstructured":"Lei Xia, Mingming Yang, and Qi Liu. 2024. Using Pre-trained Language Model for Accurate ESG Prediction. In Proceedings of the Eighth Financial Technology and Natural Language Processing and the 1st Agent AI for Scenario Planning. -, Jeju, South Korea, 1\u201322. https:\/\/aclanthology.org\/2024.finnlp-2.1\/"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Hongyang Yang Xiao-Yang Liu and Christina\u00a0Dan Wang. 2023. FinGPT: Open-Source Financial Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2306.06031\u00a0[q-fin.ST] https:\/\/arxiv.org\/abs\/2306.06031","DOI":"10.2139\/ssrn.4489826"},{"key":"e_1_3_3_2_40_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik\u00a0R Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=WE_vluYUL-X"},{"key":"e_1_3_3_2_41_2","volume-title":"International Conference on Learning Representations","author":"Zhang 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_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671801"},{"key":"e_1_3_3_2_43_2","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric\u00a0P. Xing Hao Zhang Joseph\u00a0E. Gonzalez and Ion Stoica. 2024. Judging LLM-as-a-judge with MT-bench and Chatbot Arena(NIPS\u201923). New Orleans LA USA Article 2020 29\u00a0pages."}],"event":{"name":"ICAIF '25: 6th ACM International Conference on AI in Finance","location":"Singapore Singapore","acronym":"ICAIF '25"},"container-title":["Proceedings of the 6th ACM International Conference on AI in Finance"],"original-title":[],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:26:44Z","timestamp":1763105204000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770409"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":42,"alternative-id":["10.1145\/3768292.3770409","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770409","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}