Elamur Research⌕
☰
home / papers / 2026 / FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering

FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering

Paper · 2026 · Yixi Zhou, Fan Zhang, YU Chen et al.

Summary

Answering questions over long SEC filings (10-K/10-Q) depends on finding passages that match the right company, financial metric and fiscal period, and that often contain a concrete number. Generic LLM rerankers mostly score semantic closeness. On documents spanning hundreds of pages, they tend to pick the wrong period or metric, produce unstable orderings and explain little. FinCARDS recasts evidence selection within a single filing as constraint matching. Each chunk becomes a structured "card" with fields for entities, metrics, periods, numeric spans and section cues. The question is converted into an intent specification over the same fields. A zero-shot, tournament-style pipeline then ranks the chunks. Its design mirrors a workflow of junior analyst screening, senior analyst ordering and committee adjudication. The pipeline records an audit trace for every selected chunk. On two corporate filing QA benchmarks, including FinAgentBench, the method improves early-rank retrieval over lexical and LLM reranking baselines and reduces ranking variance, with no fine-tuning. This matters in regulated finance, where evidence choices must be inspectable.

Key points

  • The pipeline has three stages: BM25 lexical recall, card-based screening with listwise reranking, and bootstrap listwise stabilization that aggregates repeated rankings. Rankings usually converge within 3–4 rounds.
  • Evaluation uses nDCG@10 and MRR@10. Gains appear consistently across six LLM backbones, suggesting the improvement comes from the structured card representation rather than from any specific model.
  • The method is zero-shot, needs no task-specific training and keeps inference cost predictable. Code is released at github.com/XanderZhou2022/FINCARDS.
  • Accuracy drops on questions that need implicit reasoning, aggregation across chunks or causal interpretation.
  • Further limitations:
    • The method requires multiple LLM calls per query.
    • It was tested only on single-document retrieval.
    • It may be sensitive to prompt and schema design.

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

🎓The University of TokyoTokyo · Japan90 works · 9,156 citations🎓Mohamed bin Zayed University of Artificial IntelligenceAbu Dhabi · United Arab Emirates124 works · 5,676 citations🎓ShanghaiTech UniversityShanghai · China13 works · 1,974 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksInformation Systems · 1,437 works

🧭 Topics 2Research subjects and languages the work is about.Question answering · 441 worksInformation retrieval & search · 473 works

Cite

Cite as Yixi Zhou, Fan Zhang, YU Chen, Haipeng Zhang, Preslav Nakov and Zhuohan Xie. 2026. FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1244

@inproceedings{zhou2026fincards,
  title = {{FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answering}},
  author = {Yixi Zhou, Fan Zhang, YU Chen, Haipeng Zhang, Preslav Nakov and Zhuohan Xie},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1244},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1244}
}

References

38 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Yiqun Chen, Qi Liu, Yi Zhang, Weiwei Sun, Xinyu Ma, Wei Yang, Daiting Shi, Jiaxin Mao, and Dawei Yin. 2025. TourRank: Utilizing large language models for documents ranking with a tournament-inspired strategy. In Proceedings of the ACM on Web Conference 2025, WWW ’25, page 1638–1652, Sydney NSW, Aust… find
  2. Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan Routledge, and William Yang Wang. 2021. FinQA: A dataset of numerical reasoning over financial data. In Proceedings of the 2021 Conference on Empirical Methods in Natural…
  3. Zhiyu Chen, Shiyang Li, Charese Smiley, Zhiqiang Ma, Sameena Shah, and William Yang Wang. 2022. ConvFinQA: Exploring the chain of numerical reasoning in conversational finance question answering. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP ’22, pa…
  4. Chanyeol Choi, Jihoon Kwon, Jaeseon Ha, Hojun Choi, Chaewoon Kim, Yongjae Lee, Jy-yong Sohn, and Alejandro Lopez-Lira. 2025a. FinDER: Financial dataset for question answering and evaluating retrieval-augmented generation. In Proceedings of the ACM International Conference on AI in Finance, ICAIF ’25… find
  5. Chanyeol Choi, Jihoon Kwon, Alejandro Lopez-Lira, Chaewoon Kim, Minjae Kim, Juneha Hwang, Jaeseon Ha, Hojun Choi, Suyeol Yun, Yongjin Kim, and Yongjae Lee. 2025b. FinAgentBench: A benchmark dataset for agentic retrieval in financial question answering. In Proceedings of the ACM International Confere… find
  6. Gordon V. Cormack, Charles L A Clarke, and Stefan Buettcher. 2009. Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’09, pages 758–759, Boston, MA, U…
  7. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. A survey on RAG meeting LLMs: Towards retrieval-augmented large language models. In Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, page 6491–6501, Ba…
  8. Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, and Furu Wei. 2022. LayoutLMv3: Pre-training for document AI with unified text and image masking. In Proceedings of the ACM International Conference on Multimedia, MM ’22, page 4083–4091, Lisboa, Portugal. Association for Computing Machinery.
  9. Pranab Islam, Anand Kannappan, Douwe Kiela, Rebecca Qian, Nino Scherrer, and Bertie Vidgen. 2023. FinanceBench: A new benchmark for financial question answering. arXiv preprint arXiv:2311.11944. — [arXiv:2311.11944](https://arxiv.org/abs/2311.11944) find
  10. Bo Li, Tian Tian, Zhenghua Xu, Hao Cheng, Shikun Zhang, and Wei Ye. 2026a. Modeling uncertainty trends for timely retrieval in dynamic RAG. In Proceedings of the AAAI Conference on Artificial Intelligence, AAAI ’26, pages 31527–31535, Singapore. AAAI Press. find
  11. Bo Li, Mingda Wang, Gexiang Fang, Shikun Zhang, and Wei Ye. 2026b. Retrieval as generation: A unified framework with self-triggered information planning. arXiv preprint arXiv:2604.11407.
  12. Zhaoyang Liu, Xiaocong Du, Yixi Zhou, Ye Shi, and Haipeng Zhang. 2026a. Fine-grained classification of A million life trajectories from wikipedia. arXiv preprint arXiv:2602.04503. — [arXiv:2602.04503](https://arxiv.org/abs/2602.04503) find
  13. Zhongyang Liu, Haoyu Pei, Xiangyi Xiao, Xiaocong Du, Yihui Li, Suting Hong, Kunpeng Zhang, and Haipeng Zhang. 2026b. Beyond isolated investor: Predicting startup success via roleplay-based collective agents. arXiv preprint arXiv:2512.22608. — [arXiv:2512.22608](https://arxiv.org/abs/2512.22608) find
  14. Zhuang Liu, Degen Huang, Kaiyu Huang, Zhuang Li, and Jun Zhao. 2020. FinBERT: A pre-trained financial language representation model for financial text mining. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJ-CAI ’20, pages 4513–4519, Yokohama, Japan. I… find
  15. Siqi Ma, Jiajie Huang, Fan Zhang, Jinlin Wu, Yue Shen, Guohui Fan, Zhu Zhang, and Zelin Zang. 2026. MedLa: A logic-driven multi-agent framework for complex medical reasoning with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40 of AAAI ’26, pages 845… find
  16. Xueguang Ma, Xinyu Zhang, Ronak Pradeep, and Jimmy Lin. 2023. Zero-shot listwise document reranking with a large language model. arXiv preprint arXiv:2305.02156. find
  17. Ahmed Masry, Do Xuan Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022. ChartQA: A benchmark for question answering about charts with visual and logical reasoning. In Findings of the Association for Computational Linguistics: ACL 2022, ACL Findings ’22, pages 2263–2279, Dublin, Ireland. Associ…
  18. Ying Nie, Binwei Yan, Tianyu Guo, Hao Liu, Haoyu Wang, Wei He, Binfan Zheng, Weihao Wang, Qiang Li, Weijian Sun, Yunhe Wang, and Dacheng Tao. 2025. CFinBench: A comprehensive Chinese financial benchmark for large language models. In Proceedings of the 2025 Conference of the Nations of the Americas C… find
  19. Haoyu Pei, Zhongyang Liu, Xiangyi Xiao, Xiaocong Du, Haipeng Zhang, Kunpeng Zhang, and Suting Hong. 2025. The gaining paths to investment success: Information-driven LLM graph reasoning for venture capital prediction. arXiv preprint arXiv:2512.23489. — [arXiv:2512.23489](https://arxiv.org/abs/2512.23489) find
  20. Xueqing Peng, Triantafillos Papadopoulos, Efstathia Soufleri, Polydoros Giannouris, Ruoyu Xiang, Yan Wang, Lingfei Qian, Jimin Huang, Qianqian Xie, and Sophia Ananiadou. 2025. Plutus: Benchmarking large language models in low-resource Greek finance. In Proceedings of the 2025 Conference on Empirical…
  21. Zhen Qin, Rolf Jagerman, Kai Hui, Honglei Zhuang, Junru Wu, Le Yan, Jiaming Shen, Tianqi Liu, Jialu Liu, Donald Metzler, Xuanhui Wang, and Michael Bendersky. 2024. Large language models are effective text rankers with pairwise ranking prompting. In Findings of the Association for Computational Lingu…
  22. Stephen Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: BM25 and beyond. Foundations and Trends in Information Retrieval, 3(4):333–389. find
  23. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: language agents with verbal reinforcement learning. In Proceedings of the International Conference on Neural Information Processing Systems, NeurIPS ’23, New Orleans, LA, USA.
  24. Weiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, and Zhaochun Ren. 2023. Is ChatGPT good at search? Investigating large language models as re-ranking agents. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP ’23,…
  25. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-consistency improves chain of thought reasoning in language models. In Proceedings of the International Conference on Learning Representations, ICLR ’23, Kigali, Rwanda. Ope…
  26. Qianqian Xie, Weiguang Han, Zhengyu Chen, Ruoyu Xiang, Xiao Zhang, Yueru He, Mengxi Xiao, Dong Li, Yongfu Dai, Duanyu Feng, Yijing Xu, Haoqiang Kang, Ziyan Kuang, Chenhan Yuan, Kailai Yang, Zheheng Luo, Tianlin Zhang, Zhiwei Liu, Guojun Xiong, Zhiyang Deng, Yuechen Jiang, Zhiyuan Yao, Haohang Li, Ya… find
  27. Qianqian Xie, Weiguang Han, Xiao Zhang, Yanzhao Lai, Min Peng, Alejandro Lopez-Lira, and Jimin Huang. 2023. PIXIU: A large language model, instruction data and evaluation benchmark for finance. In Proceedings of the International Conference on Neural Information Processing Systems, NeurIPS ’23, New… find
  28. Zhuohan Xie, Dhruv Sahnan, Debopriyo Banerjee, Georgi Georgiev, Rushil Thareja, Hachem Madmoun, Jinyan Su, Aaryamonvikram Singh, Yuxia Wang, Rui Xing, Fajri Koto, Haonan Li, Ivan Koychev, Tanmoy Chakraborty, Salem Lahlou, Veselin Stoyanov, and Preslav Nakov. 2025. FinChain: A symbolic benchmark for…
  29. Tiancheng Xing, Jerry Li, Yixuan Du, and Xiyang Hu. 2025. Are llms reliable rankers? rank manipulation via two-stage token optimization. arXiv preprint arXiv:2510.06732.
  30. Shijia Xu, Yu Wang, Xiaolong Jia, Zhou Wu, Kai Liu, and April Xiaowen Dong. 2026a. RCBSF: A multi-agent framework for automated contract revision via stackelberg game. arXiv preprint arXiv:2604.10740.
  31. Shijia Xu, Zhou Wu, Xiaolong Jia, Yu Wang, Kai Liu, and April Xiaowen Dong. 2026b. Self-correcting RAG: Enhancing faithfulness via MMKP context selection and NLI-guided MCTS. arXiv preprint arXiv:2604.10734.
  32. Yehui Yang, Zelin Zang, Changxi Chi, Jingbo Zhou, Xienan Zheng, Yuzhe Jia, Chang Yu, Jinlin Wu, Fuji Yang, Jiebo Luo, Zhen Lei, and Stan Z. Li. 2026. MAT-Cell: A multi-agent tree-structured reasoning framework for batch-level single-cell annotation. arXiv preprint arXiv:2604.06269. — [arXiv:2604.06269](https://arxiv.org/abs/2604.06269) find
  33. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023a. Tree of thoughts: Deliberate problem solving with large language models. In Proceedings of the International Conference on Neural Information Processing Systems, NeurIPS ’23, New Orleans, LA, US… find
  34. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2023b. ReAct: Synergizing reasoning and acting in language models. In Proceedings of the International Conference on Learning Representations, ICLR ’23, Kigali, Rwanda. OpenReview.net.
  35. Yixi Zhou, Fan Zhang, Zhiqiao Guo, Yu Chen, Haipeng Zhang, Preslav Nakov, and Zhuohan Xie. 2026. Sql-structeval: Structural evaluation of llm text-to-sql generation. arXiv preprint arXiv:2604.06736. — [arXiv:2604.06736](https://arxiv.org/abs/2604.06736) find
  36. 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. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics…
  37. Shengyao Zhuang, Honglei Zhuang, Bevan Koopman, and Guido Zuccon. 2024. A setwise approach for effective and highly efficient zero-shot ranking with large language models. In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 3… find
  38. Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In Proceedings of the International Conference on Learning Representations, ICLR ’21, Virtual Ev…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhou-2026-fincards-card-based-analyst-reranking/