{"total":26,"rows":[{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2203.06482","title":"FiNER: Financial Numeric Entity Recognition for XBRL Tagging","created":"2022-03-12","cited_by_count":50,"area":null},{"id":"2311.08545","title":"Efficient Continual Pre-training for Building Domain Specific Large Language Models","created":"2023-11-14","cited_by_count":34,"area":null},{"id":"2506.01732","title":"Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training","created":"2025-06-02","cited_by_count":20,"area":null},{"id":"2306.03723","title":"Financial Numeric Extreme Labelling: A Dataset and Benchmarking for XBRL Tagging","created":"2023-06-06","cited_by_count":12,"area":null},{"id":"2308.14634","title":"Breaking the Bank with ChatGPT: Few-Shot Text Classification for Finance","created":"2023-08-28","cited_by_count":12,"area":null},{"id":"2210.09163","title":"KPI-EDGAR: A Novel Dataset and Accompanying Metric for Relation Extraction from Financial Documents","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2407.15892","title":"Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training","created":"2024-07-22","cited_by_count":6,"area":null},{"id":"2506.08762","title":"EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2404.06162","title":"Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports","created":"2024-04-09","cited_by_count":5,"area":null},{"id":"2305.17457","title":"Financial misstatement detection: a realistic evaluation","created":"2023-05-27","cited_by_count":4,"area":null},{"id":"2310.13312","title":"Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2409.17827","title":"BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2307.13900","title":"FinTree: Financial Dataset Pretrain Transformer Encoder for Relation Extraction","created":"2023-07-26","cited_by_count":2,"area":null},{"id":"2402.09916","title":"BUSTER: a \"BUSiness Transaction Entity Recognition\" dataset","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2208.11334","title":"Next-Year Bankruptcy Prediction from Textual Data: Benchmark and Baselines","created":"2022-08-24","cited_by_count":1,"area":null},{"id":"2303.13475","title":"Learning Semantic Text Similarity to rank Hypernyms of Financial Terms","created":"2023-03-20","cited_by_count":1,"area":null},{"id":"2502.15411","title":"HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2508.19313","title":"Are Companies Taking AI Risks Seriously? A Systematic Analysis of Companies' AI Risk Disclosures in SEC 10-K forms","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2602.06031","title":"AP-OOD: Attention Pooling for Out-of-Distribution Detection","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2301.06901","title":"Graph-based Keyword Planning for Legal Clause Generation from Topics","created":"2023-01-07","cited_by_count":0,"area":null},{"id":"2307.03410","title":"Scalable High-Dimensional Multivariate Linear Regression for Feature-Distributed Data","created":"2023-07-07","cited_by_count":0,"area":null},{"id":"2507.15349","title":"Scaling Decentralized Learning with FLock","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2605.28714","title":"IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.18192","title":"The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.08346","title":"Grounded Event Extraction from SEC 8-K Filings with a Fine-Grained Taxonomy","created":"2026-07-09","cited_by_count":0,"area":null}],"next_cursor":null}