Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, Mengnan Du. Findings of the Association for Computational Linguistics ACL 2024. 2024.

Dong Shu, Xuansheng Wu, Haiyan Zhao, Daking Rai, Ziyu Yao, Ninghao Liu, Mengnan Du. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

Dong Shu, Haiyan Zhao, Jingyu Hu, Weiru Liu, Ali Payani, Lu Cheng, Mengnan Du. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

Anyi Wang, Dong Shu, Yifan Wang, Yunpu Ma, Mengnan Du. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du, Ninghao Liu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Predicting corporate earnings surprises is a profitable yet challenging task, as accurate forecasts can inform significant investment decisions. However, progress in this domain has been constrained by a reliance on expensive, proprietary, and text-only data, limiting the development of advanced models. To address this gap, we introduce \textbf{FinCall-Surprise} (Financial Conference Call for Earning Surprise Prediction), the first large-scale, open-source, and multi-modal dataset for earnings surprise prediction. Comprising 2,688 unique corporate conference calls from 2019 to 2021, our dataset features word-to-word conference call textual transcripts, full audio recordings, and corresponding presentation slides. We establish a comprehensive benchmark by evaluating 26 state-of-the-art unimodal and multi-modal LLMs. Our findings reveal that (1) while many models achieve high accuracy, this performance is often an illusion caused by significant class imbalance in the real-world data. (2) Some specialized financial models demonstrate unexpected weaknesses in instruction-following and language generation. (3) Although incorporating audio and visual modalities provides some performance gains, current models still struggle to leverage these signals effectively. These results highlight critical limitations in the financial reasoning capabilities of existing LLMs and establish a challenging new baseline for future research.