{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T19:56:39Z","timestamp":1783972599714,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770341","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"299-307","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Reasoning or Overthinking: Evaluating Large Language Models on Financial Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6794-044X","authenticated-orcid":false,"given":"Dimitris","family":"Vamvourellis","sequence":"first","affiliation":[{"name":"BlackRock, Inc., New York, USA"}],"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., New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_3_2","unstructured":"Dogu Araci. 2019. Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1908.10063 (2019)."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Gagan Bhatia El\u00a0Moatez\u00a0Billah Nagoudi Hasan Cavusoglu and Muhammad Abdul-Mageed. 2024. Fintral: A family of gpt-4 level multimodal financial large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.10986 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.774"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Marcel Binz and Eric Schulz. 2023. Using cognitive psychology to understand GPT-3. Proceedings of the National Academy of Sciences 120 6 (2023) e2218523120.","DOI":"10.1073\/pnas.2218523120"},{"key":"e_1_3_3_2_6_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_7_2","unstructured":"Xingyu Chen Jiahao Xu Tian Liang Zhiwei He Jianhui Pang Dian Yu Linfeng Song Qiuzhi Liu Mengfei Zhou Zhuosheng Zhang et\u00a0al. 2024. Do not think that much for 2+ 3=? on the overthinking of o1-like llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.21187 (2024)."},{"key":"e_1_3_3_2_8_2","unstructured":"Yanxi Chen Xuchen Pan Yaliang Li Bolin Ding and Jingren Zhou. 2024. A simple and provable scaling law for the test-time compute of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.19477 (2024)."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"George Fatouros Kostas Metaxas John Soldatos and Dimosthenis Kyriazis. 2024. Can Large Language Models beat wall street? Evaluating GPT-4\u2019s impact on financial decision-making with MarketSenseAI. Neural Computing and Applications (2024) 1\u201326.","DOI":"10.2139\/ssrn.4693849"},{"key":"e_1_3_3_2_10_2","unstructured":"Guhao Feng Bohang Zhang Yuntian Gu Haotian Ye Di He and Liwei Wang. 2023. Towards revealing the mystery behind chain of thought: a theoretical perspective. Advances in Neural Information Processing Systems 36 (2023) 70757\u201370798."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Paul Glasserman and Caden Lin. 2023. Assessing look-ahead bias in stock return predictions generated by gpt sentiment analysis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.17322 (2023).","DOI":"10.2139\/ssrn.4586726"},{"key":"e_1_3_3_2_12_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et\u00a0al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12948 (2025)."},{"key":"e_1_3_3_2_13_2","unstructured":"Tingxu Han Zhenting Wang Chunrong Fang Shiyu Zhao Shiqing Ma and Zhenyu Chen. 2024. Token-budget-aware llm reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.18547 (2024)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Allen\u00a0H Huang Hui Wang and Yi Yang. 2023. FinBERT: A large language model for extracting information from financial text. Contemporary Accounting Research 40 2 (2023) 806\u2013841.","DOI":"10.1111\/1911-3846.12832"},{"key":"e_1_3_3_2_15_2","unstructured":"Mingyu Jin Qinkai Yu Dong Shu Haiyan Zhao Wenyue Hua Yanda Meng Yongfeng Zhang and Mengnan Du. 2024. The impact of reasoning step length on large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.04925 (2024)."},{"key":"e_1_3_3_2_16_2","unstructured":"Daniel Kahneman. 2011. Thinking fast and slow. Farrar Straus and Giroux (2011)."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Alex Kim Maximilian Muhn and Valeri Nikolaev. 2023. Bloated disclosures: can ChatGPT help investors process information? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.10224 (2023).","DOI":"10.2139\/ssrn.4425527"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Alex\u00a0G Kim and Valeri\u00a0V Nikolaev. 2024. Context-Based Interpretation of Financial Information. Journal of Accounting Research (2024).","DOI":"10.1111\/1475-679X.12593"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"J\u00a0Peter Kincaid Robert\u00a0P Fishburne\u00a0Jr Richard\u00a0L Rogers and Brad\u00a0S Chissom. 1975. Derivation of new readability formulas (automated readability index fog count and flesch reading ease formula) for navy enlisted personnel. (1975).","DOI":"10.21236\/ADA006655"},{"key":"e_1_3_3_2_20_2","unstructured":"Takeshi Kojima Shixiang\u00a0Shane Gu Machel Reid Yutaka Matsuo and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022) 22199\u201322213."},{"key":"e_1_3_3_2_21_2","unstructured":"Thanos Konstantinidis Giorgos Iacovides Mingxue Xu Tony\u00a0G Constantinides and Danilo Mandic. 2024. Finllama: Financial sentiment classification for algorithmic trading applications. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.12285 (2024)."},{"key":"e_1_3_3_2_22_2","unstructured":"Andrew\u00a0K Lampinen Ishita Dasgupta Jacob Hilton Aida Nematzadeh Joshua\u00a0B Tenenbaum Christopher Clark and Samuel\u00a0R Bowman. 2022. Can Language Models Learn from Explanations in Context? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.02329 (2022). https:\/\/arxiv.org\/abs\/2204.02329"},{"key":"e_1_3_3_2_23_2","unstructured":"Zhaowei Liu Xin Guo Fangqi Lou Lingfeng Zeng Jinyi Niu Zixuan Wang Jiajie Xu Weige Cai Ziwei Yang Xueqian Zhao et\u00a0al. 2025. Fin-r1: A large language model for financial reasoning through reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.16252 (2025)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Alejandro Lopez-Lira and Yuehua Tang. 2023. Can chatgpt forecast stock price movements? return predictability and large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.07619 (2023).","DOI":"10.2139\/ssrn.4412788"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Pekka Malo Ankur Sinha Pekka Korhonen Jyrki Wallenius and Pyry Takala. 2014. Good debt or bad debt: Detecting semantic orientations in economic texts. Journal of the Association for Information Science and Technology 65 4 (2014) 782\u2013796.","DOI":"10.1002\/asi.23062"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Niklas Muennighoff Zitong Yang Weijia Shi Xiang\u00a0Lisa Li Li Fei-Fei Hannaneh Hajishirzi Luke Zettlemoyer Percy Liang Emmanuel Cand\u00e8s and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.19393 (2025).","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"e_1_3_3_2_27_2","unstructured":"Ummara Mumtaz and Summaya Mumtaz. 2023. Potential of ChatGPT in predicting stock market trends based on Twitter Sentiment Analysis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.06273 (2023)."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Matthew Renze and Erhan Guven. 2024. Self-reflection in llm agents: Effects on problem-solving performance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.06682 (2024).","DOI":"10.1109\/FLLM63129.2024.10852426"},{"key":"e_1_3_3_2_29_2","unstructured":"Noah Shinn Federico Cassano Beck Labash Ashwin Gopinath Karthik Narasimhan and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning 2023. URL https:\/\/arxiv. org\/abs\/2303.11366 (2023)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Parshin Shojaee Iman Mirzadeh Keivan Alizadeh Maxwell Horton Samy Bengio and Mehrdad Farajtabar. 2025. The illusion of thinking: Understanding the strengths and limitations of reasoning models via the lens of problem complexity. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.06941 (2025).","DOI":"10.70777\/si.v2i6.15919"},{"key":"e_1_3_3_2_31_2","unstructured":"Charlie Snell Jaehoon Lee Kelvin Xu and Aviral Kumar. 2024. Scaling llm test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.03314 (2024)."},{"key":"e_1_3_3_2_32_2","unstructured":"Rick Steinert and Saskia Altmann. 2023. Linking microblogging sentiments to stock price movement: An application of GPT-4. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.16771 (2023)."},{"key":"e_1_3_3_2_33_2","unstructured":"Yang Sui Yu-Neng Chuang Guanchu Wang Jiamu Zhang Tianyi Zhang Jiayi Yuan Hongyi Liu Andrew Wen Shaochen Zhong Hanjie Chen et\u00a0al. 2025. Stop overthinking: A survey on efficient reasoning for large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.16419 (2025)."},{"key":"e_1_3_3_2_34_2","unstructured":"Jean-Francois Ton Muhammad\u00a0Faaiz Taufiq and Yang Liu. 2024. Understanding Chain-of-Thought in LLMs through Information Theory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.11984 (2024)."},{"key":"e_1_3_3_2_35_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_2_36_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837."},{"key":"e_1_3_3_2_37_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2303.17564 (2023)."},{"key":"e_1_3_3_2_38_2","volume-title":"The 4th Workshop on Mathematical Reasoning and AI at NeurIPS","author":"Wu Yangzhen","year":"2024","unstructured":"Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, and Yiming Yang. 2024. Scaling inference computation: Compute-optimal inference for problem-solving with language models. In The 4th Workshop on Mathematical Reasoning and AI at NeurIPS , Vol.\u00a024."},{"key":"e_1_3_3_2_39_2","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Tom Griffiths Yuan Cao and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems 36 (2023) 11809\u201311822."},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Shengjia Zhang Junjie Wu Jiawei Chen Changwang Zhang Xingyu Lou Wangchunshu Zhou Sheng Zhou Can Wang and Jun Wang. 2025. OThink-R1: Intrinsic Fast\/Slow Thinking Mode Switching for Over-Reasoning Mitigation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.02397 (2025). 10.48550\/arXiv.2506.02397arXiv:https:\/\/arXiv.org\/abs\/2506.02397 [cs.AI].","DOI":"10.48550\/arXiv.2506.02397"},{"key":"e_1_3_3_2_41_2","unstructured":"Denny Zhou Nathanael Sch\u00e4rli Le Hou Jason Wei Nathan Scales Xuezhi Wang Dale Schuurmans Claire Cui Olivier Bousquet Quoc Le et\u00a0al. 2022. Least-to-most prompting enables complex reasoning in large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.10625 (2022)."},{"key":"e_1_3_3_2_42_2","unstructured":"Alireza\u00a0S Ziabari Nona Ghazizadeh Zhivar Sourati Farzan Karimi-Malekabadi Payam Piray and Morteza Dehghani. 2025. Reasoning on a spectrum: Aligning llms to system 1 and system 2 thinking. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.12470 (2025)."}],"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":"2025-11-14T07:28:59Z","timestamp":1763105339000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770341"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":41,"alternative-id":["10.1145\/3768292.3770341","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770341","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"}}]}}