---
title: "FinCall-Surprise — paper by Shu et al. (2026)"
description: "The authors release FinCall-Surprise, an openly available dataset of 2,688 US earnings conference calls from… 12% accuracy. 62 references."
authors: ["Dong Shu", "Yanguang Liu", "Huopu Zhang", "Mengnan Du"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.610/"
doi: "10.18653/v1/2026.acl-long.610"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/shu-2026-fincall-surprise-large-scale-multi/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shu-2026-fincall-surprise-large-scale-multi/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/12/) / FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction

# FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction

**Authors:** [Dong Shu](https://md.research.elamur.ai/free/en/authors/dong-shu/), [Yanguang Liu](https://md.research.elamur.ai/free/en/authors/yanguang-liu/), [Huopu Zhang](https://md.research.elamur.ai/free/en/authors/huopu-zhang/) and [Mengnan Du](https://md.research.elamur.ai/free/en/authors/mengnan-du/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.610/) · [PDF](https://aclanthology.org/2026.acl-long.610.pdf) · [DOI 10.18653/v1/2026.acl-long.610](https://doi.org/10.18653/v1/2026.acl-long.610) · [OpenAlex](https://openalex.org/W4414971017)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
Forecasting whether a company's reported earnings per share will beat or miss market expectations can drive investment decisions. Research on this task has relied mostly on costly, proprietary, transcript-only data. The authors release FinCall-Surprise, an openly available dataset of 2,688 US earnings conference calls from 2019–2021. Each call includes three aligned modalities: the full transcript with speaker roles, the audio recording, and the presentation slides. Calls are matched at the event level using quarterly periods and call titles, and each is labelled as a positive or negative earnings surprise.

The authors benchmark 26 text-only and multimodal LLMs. High accuracy scores turn out to be misleading because most calls are positive surprises, so models that mostly predict the majority class look strong. Some finance-tuned models fail badly. Adding audio or slides helps only some models. These results expose weak financial reasoning in current LLMs and give the community a demanding open baseline.

## Key points
- **Firm selection and sources:**
  - Firms qualified with market capitalization above $1B and average daily trading volume above $50M, giving an initial pool of more than 4,000 firms.
  - Transcripts and audio were scraped from corporate websites.
  - Seeking Alpha was used to find call dates, and EarningsCast to sync audio.
  - Slides came from Bloomberg News and company sites.
- **Dataset size and class balance:** The dataset covers 919 calls (2019), 704 (2020) and 1,065 (2021). Positive surprises make up 79%, 86% and 89% of calls in those years, respectively.
- **Failing finance-tuned models:** Fin-LLaMa3 reached only 12% accuracy and LLaMa-RAG only 10%. Causes were a bias toward "negative" predictions, ignoring the required answer format, and degraded text generation, which the authors attribute to over-finetuning.
- **Mixed effect of extra modalities:**
  - Within Qwen-2.5, the 14B text-only model scored 0.80, while the 7B image-text and 7B audio-text models scored 0.82 and 0.84.
  - LLaMa-3.2 dropped from 0.78 (3B text-only) to 0.58 (11B image-text).
  - Gemma-3n scored 0.34 and DeSTA-2.5 scored 0.54.
- **Availability:** The dataset is hosted at github.com/Tizzzzy/FinCall-Surprise.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Georgia Institute of Technology](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/) — University, Atlanta, United States · 133 works · 24,497 citations
- [Northwestern University](https://md.research.elamur.ai/free/en/universities/northwestern-university/) — University, Evanston, United States · 41 works · 2,194 citations
- [Chinese University of Hong Kong, Shenzhen](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong-shenzhen/) — University, Shenzhen, China · 47 works · 2,596 citations
- [New Jersey Institute of Technology](https://md.research.elamur.ai/free/en/universities/new-jersey-institute-of-technology/) — University, Newark, United States · 15 works · 1,333 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🎯 Decision Sciences](https://md.research.elamur.ai/free/en/shelves/decision-sciences/) · 209 works · [🎯 Management Science and Operations Research](https://md.research.elamur.ai/free/en/shelves/decision-sciences/management-science-and-operations-research/) · 108 works · [💼 Business, Management and Accounting](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/) · 32 works · [💼 Accounting](https://md.research.elamur.ai/free/en/shelves/business-management-and-accounting/accounting/) · 5 works

🧭 Topics (2): [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,220 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: Dong Shu, Yanguang Liu, Huopu Zhang and Mengnan Du. 2026. FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{shu2026fincall,
  title = {{FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction}},
  author = {Dong Shu, Yanguang Liu, Huopu Zhang and Mengnan Du},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.610},
  url = {https://doi.org/10.18653/v1/2026.acl-long.610}
}
```

- [← previous Financial Causal QA via Instruction and Prompt Tuning of Gemma3-12B](https://md.research.elamur.ai/free/en/papers/trivedi-2026-financial-causal-qa-instruction-prompt/)
- [next → Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs](https://md.research.elamur.ai/free/en/papers/peisakhovsky-2026-fine-grained-detection-context-grounded/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/12/)

## References

62 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Khaled Alsabah. 2025. Love me do: Twitter likes and earnings surprise. Journal of Behavioral Finance, 26(3):283–302. [find](https://scholar.google.com/scholar?q=Khaled+Alsabah%2E+2025%2E+Love+me+do%3A+Twitter+likes+and+earnings+surprise%2E+Journal+of+Behavioral+Finance%2C+26%283%29%3A283%E2%80%93302%2E)
2. Dogu Araci. 2019. Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063. [find](https://scholar.google.com/scholar?q=Dogu+Araci%2E+2019%2E+Finbert%3A+Financial+sentiment+analysis+with+pre%2Dtrained+language+models%2E+arXiv+preprint+arXiv%3A1908%2E10063%2E)
3. Alisson Azzolini, Junjie Bai, Hannah Brandon, Jiaxin Cao, Prithvijit Chattopadhyay, Huayu Chen, Jinju Chu, Yin Cui, Jenna Diamond, Yifan Ding, and 1 others. 2025. Cosmos-reason1: From physical common sense to embodied reasoning. arXiv preprint arXiv:2503.15558. — [arXiv:2503.15558](https://arxiv.org/abs/2503.15558) [find](https://scholar.google.com/scholar?q=Alisson+Azzolini%2C+Junjie+Bai%2C+Hannah+Brandon%2C+Jiaxin+Cao%2C+Prithvijit+Chattopadhyay%2C+Huayu+Chen%2C+Jinju+Chu%2C+Yin+Cui%2C+Jenna+Diamond%2C+Yifan+Ding%2C+and+1+others%2E+2025%2E+Cosmos%2Dreason1%3A+From+physical+common+)
4. Sanjay W Bissessur and David Veenman. 2016. Analyst information precision and small earnings surprises. Review of Accounting Studies, 21(4):1327–1360. [find](https://scholar.google.com/scholar?q=Sanjay+W+Bissessur+and+David+Veenman%2E+2016%2E+Analyst+information+precision+and+small+earnings+surprises%2E+Review+of+Accounting+Studies%2C+21%284%29%3A1327%E2%80%931360%2E)
5. Taha Borhani. 2024. Twitter financial news sentiment dataset. Kaggle. Accessed: 2025-09-13. [find](https://scholar.google.com/scholar?q=Taha+Borhani%2E+2024%2E+Twitter+financial+news+sentiment+dataset%2E+Kaggle%2E+Accessed%3A+2025%2D09%2D13%2E)
6. Jian Chen, Peilin Zhou, Yining Hua, Yingxin Loh, Kehui Chen, Ziyuan Li, Bing Zhu, and Junwei Liang. 2024. Fintextqa: A dataset for long-form financial question answering. arXiv preprint arXiv:2405.09980. [find](https://scholar.google.com/scholar?q=Jian+Chen%2C+Peilin+Zhou%2C+Yining+Hua%2C+Yingxin+Loh%2C+Kehui+Chen%2C+Ziyuan+Li%2C+Bing+Zhu%2C+and+Junwei+Liang%2E+2024%2E+Fintextqa%3A+A+dataset+for+long%2Dform+financial+question+answering%2E+arXiv+preprint+arXiv%3A2405%2E099)
7. Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan Routledge, and 1 others. 2021. [Finqa: A dataset of numerical reasoning over financial data](https://md.research.elamur.ai/free/en/papers/chen-2021-finqa-dataset-numerical-reasoning-over/). arXiv preprint arXiv:2109.00122.
8. Daixuan Cheng, Yuxian Gu, Shaohan Huang, Junyu Bi, Minlie Huang, and Furu Wei. 2024. [Instruction pre-training: Language models are supervised multitask learners](https://md.research.elamur.ai/free/en/papers/cheng-2024-instruction-pre-training-language-models/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 2529–2550, Miami, Florida, USA. Associati…
9. Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, Yuanjun Lv, Jinzheng He, Junyang Lin, Chang Zhou, and Jingren Zhou. 2024. [Qwen2-audio technical report](https://md.research.elamur.ai/free/en/papers/chu-2024-qwen2-audio-technical-report/). arXiv preprint arXiv:2407.10759.
10. Keith Cortis, André Freitas, Tobias Daudert, Manuela Huerlimann, Manel Zarrouk, Siegfried Handschuh, and Brian Davis. 2017. SemEval-2017 task 5: Fine-grained sentiment analysis on financial microblogs and news. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017),… [find](https://scholar.google.com/scholar?q=Keith+Cortis%2C+Andr%C3%A9+Freitas%2C+Tobias+Daudert%2C+Manuela+Huerlimann%2C+Manel+Zarrouk%2C+Siegfried+Handschuh%2C+and+Brian+Davis%2E+2017%2E+SemEval%2D2017+task+5%3A+Fine%2Dgrained+sentiment+analysis+on+financial+microblogs)
11. Vasant Dhar and Dashin Chou. 2001. A comparison of nonlinear methods for predicting earnings surprises and returns. IEEE Transactions on Neural networks, 12(4):907–921. [find](https://scholar.google.com/scholar?q=Vasant+Dhar+and+Dashin+Chou%2E+2001%2E+A+comparison+of+nonlinear+methods+for+predicting+earnings+surprises+and+returns%2E+IEEE+Transactions+on+Neural+networks%2C+12%284%29%3A907%E2%80%93921%2E)
12. Zihan Dong, Xinyu Fan, and Zhiyuan Peng. 2024. Fn-spid: A comprehensive financial news dataset in time series. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 4918–4927. [find](https://scholar.google.com/scholar?q=Zihan+Dong%2C+Xinyu+Fan%2C+and+Zhiyuan+Peng%2E+2024%2E+Fn%2Dspid%3A+A+comprehensive+financial+news+dataset+in+time+series%2E+In+Proceedings+of+the+30th+ACM+SIGKDD+Conference+on+Knowledge+Discovery+and+Data+Mining%2C+)
13. Jeffrey T Doyle, Russell J Lundholm, and Mark T Soliman. 2006. The extreme future stock returns following i/b/e/s earnings surprises. Journal of Accounting Research, 44(5):849–887. [find](https://scholar.google.com/scholar?q=Jeffrey+T+Doyle%2C+Russell+J+Lundholm%2C+and+Mark+T+Soliman%2E+2006%2E+The+extreme+future+stock+returns+following+i%2Fb%2Fe%2Fs+earnings+surprises%2E+Journal+of+Accounting+Research%2C+44%285%29%3A849%E2%80%93887%2E)
14. Eli Bartov. 1992. Patterns in Unexpected Earnings as an Explanation for Post-Announcement Drift. The Accounting Review, 67(3):610–622. Publisher: American Accounting Association. [find](https://scholar.google.com/scholar?q=Eli+Bartov%2E+1992%2E+Patterns+in+Unexpected+Earnings+as+an+Explanation+for+Post%2DAnnouncement+Drift%2E+The+Accounting+Review%2C+67%283%29%3A610%E2%80%93622%2E+Publisher%3A+American+Accounting+Association%2E)
15. Duanyu Feng, Yongfu Dai, Jimin Huang, Yifang Zhang, Qianqian Xie, Weiguang Han, Zhengyu Chen, Alejandro Lopez-Lira, and Hao Wang. 2023. Empowering many, biasing a few: Generalist credit scoring through large language models. arXiv preprint arXiv:2310.00566. — [arXiv:2310.00566](https://arxiv.org/abs/2310.00566) [find](https://scholar.google.com/scholar?q=Duanyu+Feng%2C+Yongfu+Dai%2C+Jimin+Huang%2C+Yifang+Zhang%2C+Qianqian+Xie%2C+Weiguang+Han%2C+Zhengyu+Chen%2C+Alejandro+Lopez%2DLira%2C+and+Hao+Wang%2E+2023%2E+Empowering+many%2C+biasing+a+few%3A+Generalist+credit+scoring+throug)
16. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
17. John C Heater, Ye Liu, Qin Tan, and Frank Zhang. 2025. Winning is not enough: Changing landscapes of earnings surprises and the market reaction. Contemporary Accounting Research. [find](https://scholar.google.com/scholar?q=John+C+Heater%2C+Ye+Liu%2C+Qin+Tan%2C+and+Frank+Zhang%2E+2025%2E+Winning+is+not+enough%3A+Changing+landscapes+of+earnings+surprises+and+the+market+reaction%2E+Contemporary+Accounting+Research%2E)
18. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, and Devendra Singh Chaplot. 2023. Diego de las casas. Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée… [find](https://scholar.google.com/scholar?q=Albert+Q+Jiang%2C+Alexandre+Sablayrolles%2C+Arthur+Mensch%2C+Chris+Bamford%2C+and+Devendra+Singh+Chaplot%2E+2023%2E+Diego+de+las+casas%2E+Florian+Bressand%2C+Gianna+Lengyel%2C+Guillaume+Lample%2C+Lucile+Saulnier%2C+L%C3%A9lio+R)
19. KhazarAI. 2024. Personal-finance-r1. [https://huggingface.co/khazarai/](https://huggingface.co/khazarai/) Accessed: 2025-09-Personal-Finance-R1. 14. [↗](https://huggingface.co/khazarai/)
20. Alex Kim, Maximilian Muhn, and Valeri Nikolaev. 2024. Financial statement analysis with large language models. arXiv preprint arXiv:2407.17866. — [arXiv:2407.17866](https://arxiv.org/abs/2407.17866) [find](https://scholar.google.com/scholar?q=Alex+Kim%2C+Maximilian+Muhn%2C+and+Valeri+Nikolaev%2E+2024%2E+Financial+statement+analysis+with+large+language+models%2E+arXiv+preprint+arXiv%3A2407%2E17866%2E+%E2%80%94+%5BarXiv%3A2407%2E17866%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2407%2E17866%29)
21. Michael D Kimbrough. 2005. The effect of conference calls on analyst and market underreaction to earnings announcements. The Accounting Review, 80(1):189– 219. [find](https://scholar.google.com/scholar?q=Michael+D+Kimbrough%2E+2005%2E+The+effect+of+conference+calls+on+analyst+and+market+underreaction+to+earnings+announcements%2E+The+Accounting+Review%2C+80%281%29%3A189%E2%80%93+219%2E)
22. Ross Koval, Nicholas Andrews, and Xifeng Yan. 2023. Forecasting earnings surprises from conference call transcripts. In Findings of the association for computational linguistics: ACL 2023, pages 8197–8209. [find](https://scholar.google.com/scholar?q=Ross+Koval%2C+Nicholas+Andrews%2C+and+Xifeng+Yan%2E+2023%2E+Forecasting+earnings+surprises+from+conference+call+transcripts%2E+In+Findings+of+the+association+for+computational+linguistics%3A+ACL+2023%2C+pages+8197%E2%80%93)
23. Ross Koval, Nicholas Andrews, and Xifeng Yan. 2024. Financial forecasting from textual and tabular time series. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8289–8300. [find](https://scholar.google.com/scholar?q=Ross+Koval%2C+Nicholas+Andrews%2C+and+Xifeng+Yan%2E+2024%2E+Financial+forecasting+from+textual+and+tabular+time+series%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2024%2C+pages+8289%E2%80%93830)
24. Viet Dac Lai, Michael Krumdick, Charles Lovering, Varshini Reddy, Craig Schmidt, and Chris Tanner. 2024. Sec-qa: A systematic evaluation corpus for financial qa. arXiv preprint arXiv:2406.14394. [find](https://scholar.google.com/scholar?q=Viet+Dac+Lai%2C+Michael+Krumdick%2C+Charles+Lovering%2C+Varshini+Reddy%2C+Craig+Schmidt%2C+and+Chris+Tanner%2E+2024%2E+Sec%2Dqa%3A+A+systematic+evaluation+corpus+for+financial+qa%2E+arXiv+preprint+arXiv%3A2406%2E14394%2E)
25. Henry A Latane and Charles P Jones. 1979. Standardized unexpected earnings–1971-77. The Journal of Finance, 34(3):717–724. [find](https://scholar.google.com/scholar?q=Henry+A+Latane+and+Charles+P+Jones%2E+1979%2E+Standardized+unexpected+earnings%E2%80%931971%2D77%2E+The+Journal+of+Finance%2C+34%283%29%3A717%E2%80%93724%2E)
26. Jean Lee, Nicholas Stevens, and Soyeon Caren Han. 2025. Large language models in finance (finllms). Neural Computing and Applications, pages 1–15. [find](https://scholar.google.com/scholar?q=Jean+Lee%2C+Nicholas+Stevens%2C+and+Soyeon+Caren+Han%2E+2025%2E+Large+language+models+in+finance+%28finllms%29%2E+Neural+Computing+and+Applications%2C+pages+1%E2%80%9315%2E)
27. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2019. [BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/). CoRR, abs/1910.13461.
28. Jiazheng Li, Linyi Yang, Barry Smyth, and Ruihai Dong. 2020. Maec: A multimodal aligned earnings conference call dataset for financial risk prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 3063–3070. [find](https://scholar.google.com/scholar?q=Jiazheng+Li%2C+Linyi+Yang%2C+Barry+Smyth%2C+and+Ruihai+Dong%2E+2020%2E+Maec%3A+A+multimodal+aligned+earnings+conference+call+dataset+for+financial+risk+prediction%2E+In+Proceedings+of+the+29th+ACM+International+Con)
29. Alexandre Sablayrolles, Amélie Héliou, and 87 others. 2025. Voxtral. Preprint, arXiv:2507.13264. [find](https://scholar.google.com/scholar?q=Alexandre+Sablayrolles%2C+Am%C3%A9lie+H%C3%A9liou%2C+and+87+others%2E+2025%2E+Voxtral%2E+Preprint%2C+arXiv%3A2507%2E13264%2E)
30. Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023. [Improved baselines with visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-improved-baselines-visual-instruction-tuning/). Preprint, arXiv:2310.03744.
31. Wanlong Liu, Junying Chen, Ke Ji, Li Zhou, Wenyu Chen, and Benyou Wang. 2024. [Rag-instruct: Boosting llms with diverse retrieval-augmented instructions](https://md.research.elamur.ai/free/en/papers/liu-2025-rag-instruct-boosting-llms-diverse/). Preprint, arXiv:2501.00353.
32. Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, Chao-Han Huck Yang, Sung-Feng Huang, Chih-Kai Yang, Chee-En Yu, Chun-Wei Chen, Wei-Chih Chen, Chien-yu Huang, and 1 others. 2025. Desta2.5-audio: Toward general-purpose large audio language model with self-generated cross-modal alignment. arXiv preprint arXiv:250… — [arXiv:2507.02768](https://arxiv.org/abs/2507.02768) [find](https://scholar.google.com/scholar?q=Ke%2DHan+Lu%2C+Zhehuai+Chen%2C+Szu%2DWei+Fu%2C+Chao%2DHan+Huck+Yang%2C+Sung%2DFeng+Huang%2C+Chih%2DKai+Yang%2C+Chee%2DEn+Yu%2C+Chun%2DWei+Chen%2C+Wei%2DChih+Chen%2C+Chien%2Dyu+Huang%2C+and+1+others%2E+2025%2E+Desta2%2E5%2Daudio%3A+Toward+general%2Dpu)
33. Cheng Luo, Enrichetta Ravina, Marco Sammon, and Luis M. Viceira. 2022. Retail investors’ contrarian behavior around news, attention, and the momentum effect. Technical report, Social Science Research Network. Posted: 5 Apr 2020; Last revised: 26 May 2022. [find](https://scholar.google.com/scholar?q=Cheng+Luo%2C+Enrichetta+Ravina%2C+Marco+Sammon%2C+and+Luis+M%2E+Viceira%2E+2022%2E+Retail+investors%E2%80%99+contrarian+behavior+around+news%2C+attention%2C+and+the+momentum+effect%2E+Technical+report%2C+Social+Science+Research+)
34. Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, and 1 others. 2025. [Finmme: Benchmark dataset for financial multi-modal reasoning evaluation](https://md.research.elamur.ai/free/en/papers/luo-2025-finmme-benchmark-dataset-financial-multi/). arXiv preprint arXiv:2505.24714.
35. Vitaly Meursault, Pierre Jinghong Liang, Bryan R. Routledge, and Madeline Marco Scanlon. 2023. Pead.txt: Post-earnings-announcement drift using text. Journal of Financial and Quantitative Analysis, 58(6):2299–2326. [find](https://scholar.google.com/scholar?q=Vitaly+Meursault%2C+Pierre+Jinghong+Liang%2C+Bryan+R%2E+Routledge%2C+and+Madeline+Marco+Scanlon%2E+2023%2E+Pead%2Etxt%3A+Post%2Dearnings%2Dannouncement+drift+using+text%2E+Journal+of+Financial+and+Quantitative+Analysis%2C+58)
36. Income Numbers. 1968. An empirical evaluation of accounting. Journal of Accounting Research. [find](https://scholar.google.com/scholar?q=Income+Numbers%2E+1968%2E+An+empirical+evaluation+of+accounting%2E+Journal+of+Accounting+Research%2E)
37. OpenAI. 2025. [gpt-oss-120b & gpt-oss-20b model card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/). Preprint, arXiv:2508.10925.
38. Jane A Ou and Stephen H Penman. 1989. Financial statement analysis and the prediction of stock returns. Journal of accounting and economics, 11(4):295– 329. [find](https://scholar.google.com/scholar?q=Jane+A+Ou+and+Stephen+H+Penman%2E+1989%2E+Financial+statement+analysis+and+the+prediction+of+stock+returns%2E+Journal+of+accounting+and+economics%2C+11%284%29%3A295%E2%80%93+329%2E)
39. Varpit Patel. 2021. Google stock data. Kaggle. Accessed: 2025-09-13. [find](https://scholar.google.com/scholar?q=Varpit+Patel%2E+2021%2E+Google+stock+data%2E+Kaggle%2E+Accessed%3A+2025%2D09%2D13%2E)
40. Qingwen Liang and Matias Carrasco Kind. 2025. How does managers’ willingness to disclose affect analysts’ earning forecasts-a measurement by llms. Available at SSRN 5199752. [find](https://scholar.google.com/scholar?q=Qingwen+Liang+and+Matias+Carrasco+Kind%2E+2025%2E+How+does+managers%E2%80%99+willingness+to+disclose+affect+analysts%E2%80%99+earning+forecasts%2Da+measurement+by+llms%2E+Available+at+SSRN+5199752%2E)
41. James M Patell. 1976. Corporate forecasts of earnings per share and stock price behavior: Empirical test. Journal of accounting research, pages 246–276. [find](https://scholar.google.com/scholar?q=James+M+Patell%2E+1976%2E+Corporate+forecasts+of+earnings+per+share+and+stock+price+behavior%3A+Empirical+test%2E+Journal+of+accounting+research%2C+pages+246%E2%80%93276%2E)
42. Alexander H. Liu, Andy Ehrenberg, Andy Lo, Clément Denoix, Corentin Barreau, Guillaume Lample, Jean-Malo Delignon, Khyathi Raghavi Chandu, Patrick von Platen, Pavankumar Reddy Muddireddy, Sanchit Gandhi, Soham Ghosh, Srijan Mishra, Thomas Foubert, Abhinav Rastogi, Adam Yang, Albert Q. Jiang, Yu Qin… [find](https://scholar.google.com/scholar?q=Alexander+H%2E+Liu%2C+Andy+Ehrenberg%2C+Andy+Lo%2C+Cl%C3%A9ment+Denoix%2C+Corentin+Barreau%2C+Guillaume+Lample%2C+Jean%2DMalo+Delignon%2C+Khyathi+Raghavi+Chandu%2C+Patrick+von+Platen%2C+Pavankumar+Reddy+Muddireddy%2C+Sanchit+Gand)
43. Aman Rangapur, Haoran Wang, Ling Jian, and Kai Shu. 2025. Fin-fact: A benchmark dataset for multimodal financial fact-checking and explanation generation. In Companion Proceedings of the ACM on Web Conference 2025, WWW ’25, page 785–788, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Aman+Rangapur%2C+Haoran+Wang%2C+Ling+Jian%2C+and+Kai+Shu%2E+2025%2E+Fin%2Dfact%3A+A+benchmark+dataset+for+multimodal+financial+fact%2Dchecking+and+explanation+generation%2E+In+Companion+Proceedings+of+the+ACM+on+Web+Co)
44. Rohan Rao. 2021. Nifty 50 stock market data (2000 -2021). Kaggle. Accessed: 2025-09-13. [find](https://scholar.google.com/scholar?q=Rohan+Rao%2E+2021%2E+Nifty+50+stock+market+data+%282000+%2D2021%29%2E+Kaggle%2E+Accessed%3A+2025%2D09%2D13%2E)
45. Varshini Reddy, Rik Koncel-Kedziorski, Viet Dac Lai, Michael Krumdick, Charles Lovering, and Chris Tanner. 2024. Docfinqa: A long-context financial reasoning dataset. arXiv preprint arXiv:2401.06915. [find](https://scholar.google.com/scholar?q=Varshini+Reddy%2C+Rik+Koncel%2DKedziorski%2C+Viet+Dac+Lai%2C+Michael+Krumdick%2C+Charles+Lovering%2C+and+Chris+Tanner%2E+2024%2E+Docfinqa%3A+A+long%2Dcontext+financial+reasoning+dataset%2E+arXiv+preprint+arXiv%3A2401%2E06915%2E)
46. Ramit Sawhney, Piyush Khanna, Arshiya Aggarwal, Taru Jain, Puneet Mathur, and Rajiv Ratn Shah. 2020. VolTAGE: Volatility forecasting via text audio fusion with graph convolution networks for earnings calls. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EM… [find](https://scholar.google.com/scholar?q=Ramit+Sawhney%2C+Piyush+Khanna%2C+Arshiya+Aggarwal%2C+Taru+Jain%2C+Puneet+Mathur%2C+and+Rajiv+Ratn+Shah%2E+2020%2E+VolTAGE%3A+Volatility+forecasting+via+text+audio+fusion+with+graph+convolution+networks+for+earnings+)
47. Dong Shu, Haoyang Yuan, Yuchen Wang, Yanguang Liu, Huopu Zhang, Haiyan Zhao, and Mengnan Du. 2025. [Finchart-bench: Benchmarking financial chart comprehension in vision-language models](https://md.research.elamur.ai/free/en/papers/shu-2026-finchart-bench-benchmarking-financial-chart/). arXiv preprint arXiv:2507.14823.
48. Douglas J Skinner and Richard G Sloan. 2002. Earnings surprises, growth expectations, and stock returns or don’t let an earnings torpedo sink your portfolio. Review of accounting studies, 7(2):289–312. tarun7r. 2025. tarun7r/finance-llama-8b: A llama 3.1 8b model fine-tuned on josephgflowers/finance… [find](https://scholar.google.com/scholar?q=Douglas+J+Skinner+and+Richard+G+Sloan%2E+2002%2E+Earnings+surprises%2C+growth+expectations%2C+and+stock+returns+or+don%E2%80%99t+let+an+earnings+torpedo+sink+your+portfolio%2E+Review+of+accounting+studies%2C+7%282%29%3A289%E2%80%93312)
49. Gemma Team. 2025a. Gemma 3. [find](https://scholar.google.com/scholar?q=Gemma+Team%2E+2025a%2E+Gemma+3%2E)
50. Qwen Team. 2024. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
51. Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu, Ting He, Shuai Bai, Keqin Chen, Jialin Wang, Yang Fan, Kai Dang, and 1 others. 2025. Qwen2. 5-omni technical report. arXiv preprint arXiv:2503.20215. — [Qwen2.5-Omni Technical Report](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen2-5-omni-technical/)
52. Haobo Yuan, Xiangtai Li, Tao Zhang, Zilong Huang Huang, Shilin Xu, Shunping Ji, Yunhai Tong, Lu Qi, Jiashi Feng, and Ming-Hsuan Yang. 2025. Sa2va: Marrying sam2 with llava for dense grounded understanding of images and videos. arXiv preprint. [find](https://scholar.google.com/scholar?q=Haobo+Yuan%2C+Xiangtai+Li%2C+Tao+Zhang%2C+Zilong+Huang+Huang%2C+Shilin+Xu%2C+Shunping+Ji%2C+Yunhai+Tong%2C+Lu+Qi%2C+Jiashi+Feng%2C+and+Ming%2DHsuan+Yang%2E+2025%2E+Sa2va%3A+Marrying+sam2+with+llava+for+dense+grounded+understan)
53. Ziqiang Yuan, Kaiyuan Wang, Shoutai Zhu, Ye Yuan, Jingya Zhou, Yanlin Zhu, and Wenqi Wei. 2024. Finllms: A framework for financial reasoning dataset generation with large language models. IEEE Transactions on Big Data. [find](https://scholar.google.com/scholar?q=Ziqiang+Yuan%2C+Kaiyuan+Wang%2C+Shoutai+Zhu%2C+Ye+Yuan%2C+Jingya+Zhou%2C+Yanlin+Zhu%2C+and+Wenqi+Wei%2E+2024%2E+Finllms%3A+A+framework+for+financial+reasoning+dataset+generation+with+large+language+models%2E+IEEE+Transac)
54. Cong Zhang and Zhenzhi He. 2025. Cross-sectional spillovers of earnings surprises and asset price anomalies. Available at SSRN 5415255. [find](https://scholar.google.com/scholar?q=Cong+Zhang+and+Zhenzhi+He%2E+2025%2E+Cross%2Dsectional+spillovers+of+earnings+surprises+and+asset+price+anomalies%2E+Available+at+SSRN+5415255%2E)
55. Huopu Zhang, Yanguang Liu, and Mengnan Du. 2025. [Sae-fire: Enhancing earnings surprise predictions through sparse autoencoder feature selection](https://md.research.elamur.ai/free/en/papers/zhang-2026-sae-fire-enhancing-earnings-surprise/). arXiv preprint arXiv:2505.14420.
56. 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](https://md.research.elamur.ai/free/en/papers/zhu-2021-tat-qa-question-answering-benchmark/). arXiv preprint arXiv:2105.07624.
57. Yongqiong Zhu. 2020. Stock price prediction using the rnn model. Journal of Physics: Conference Series, 1650:032103. [find](https://scholar.google.com/scholar?q=Yongqiong+Zhu%2E+2020%2E+Stock+price+prediction+using+the+rnn+model%2E+Journal+of+Physics%3A+Conference+Series%2C+1650%3A032103%2E)
58. Yu Zhu, Xiao Liu, and Olivia R Liu Sheng. 2025. Post-earnings-announcement drift prediction: Leveraging postevent investor responses with multitask learning. Information Systems Research. [find](https://scholar.google.com/scholar?q=Yu+Zhu%2C+Xiao+Liu%2C+and+Olivia+R+Liu+Sheng%2E+2025%2E+Post%2Dearnings%2Dannouncement+drift+prediction%3A+Leveraging+postevent+investor+responses+with+multitask+learning%2E+Information+Systems+Research%2E)
59. Leon Zolotoy. 2012. Earnings surprise implicit in stock prices: which earnings forecasting models are investors using and what determines their choice? Journal of Business Finance & Accounting, 39(9-10):1161–1179. [find](https://scholar.google.com/scholar?q=Leon+Zolotoy%2E+2012%2E+Earnings+surprise+implicit+in+stock+prices%3A+which+earnings+forecasting+models+are+investors+using+and+what+determines+their+choice%3F+Journal+of+Business+Finance+%26+Accounting%2C+39%289%2D1)
60. Qwen Team. 2025b. Qwen2.5-vl. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2025b%2E+Qwen2%2E5%2Dvl%2E)
61. Manuel R Vargas, Beatriz SLP De Lima, and Alexandre G Evsukoff. 2017. Deep learning for stock market prediction from financial news articles. In 2017 IEEE international conference on computational intelligence and virtual environments for measurement systems and applications (CIVEMSA), pages 60–65.… [find](https://scholar.google.com/scholar?q=Manuel+R+Vargas%2C+Beatriz+SLP+De+Lima%2C+and+Alexandre+G+Evsukoff%2E+2017%2E+Deep+learning+for+stock+market+prediction+from+financial+news+articles%2E+In+2017+IEEE+international+conference+on+computational+int)
62. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024. [Qwen2-vl: Enhancing vision-language model’s perception of the w…](https://md.research.elamur.ai/free/en/papers/wang-2024-qwen2-vl-enhancing-vision/)

*Updated 31 October 2026*