Financial Numeric Extreme Labelling: A Dataset and Benchmarking for XBRL Tagging
Not on the map. Why?
Abstract (arXiv)
The U.S. Securities and Exchange Commission (SEC) mandates all public companies to file periodic financial statements that should contain numerals annotated with a particular label from a taxonomy. In this paper, we formulate the task of automating the assignment of a label to a particular numeral span in a sentence from an extremely large label set. Towards this task, we release a dataset, Financial Numeric Extreme Labelling (FNXL), annotated with 2,794 labels. We benchmark the performance of the FNXL dataset by formulating the task as (a) a sequence labelling problem and (b) a pipeline with span extraction followed by Extreme Classification. Although the two approaches perform comparably, the pipeline solution provides a slight edge for the least frequent labels.
Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 9 of its 30 references that are in the map. First posted on arXiv 6 Jun 2023.
Builds on
9 of 30 references.
References · 9
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2013Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Textscited by 310
- 2018AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classificationcited by 102
- 2022ECTSum: A New Benchmark Dataset For Bullet Point Summarization of Long Earnings Call Transcriptscited by 59
- 2022FiNER: Financial Numeric Entity Recognition for XBRL Taggingcited by 50
- 2021EDGAR-CORPUS: Billions of Tokens Make The World Go Roundcited by 32
- 2019Financial Event Extraction Using Wikipedia-Based Weak Supervisioncited by 11
- 2019Group, Extract and Aggregate: Summarizing a Large Amount of Finance News for Forex Movement Predictioncited by 6
- 2022A Generative Approach for Financial Causality Extractioncited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 2; 2025: 7; 2026: 2.
12 papers.
- 2024FinBen: A Holistic Financial Benchmark for Large Language Modelscited by 141
- 2024A Survey of Large Language Models in Finance (FinLLMs)cited by 79
- 2023FinEntity: Entity-level Sentiment Classification for Financial Textscited by 14
- 2025FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMscited by 14
- 2025FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasetscited by 12
- 2025Bridging Language Models and Financial Analysiscited by 4
- 2025Finance Language Model Evaluation (FLaME)cited by 4
- 2025HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filingscited by 1
- 2025FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Datacited by 1
- 2025RKEFino1: A Regulation Knowledge-Enhanced Large Language Modelcited by 1
- 2026Noise-Robust Financial Numerical Entity Attribute Taggingcited by 0
- 2026Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extractioncited by 0
- 2026Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction14 Oct 2026
- 2026Noise-Robust Financial Numerical Entity Attribute Tagging24 May 2026
- 2025FinAuditing: A Financial Taxonomy-Structured Multi-Document Benchmark for Evaluating LLMs10 Oct 2025
- 2025Finance Language Model Evaluation (FLaME)18 Jun 2025
- 2025RKEFino1: A Regulation Knowledge-Enhanced Large Language Model6 Jun 2025
- 2025FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets26 May 2025
- 2025Bridging Language Models and Financial Analysis14 Mar 2025
- 2025HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings21 Feb 2025
- 2025FinBloom: Knowledge Grounding Large Language Model with Real-time Financial Data4 Feb 2025
- 2024FinBen: A Holistic Financial Benchmark for Large Language Models20 Feb 2024
- 2024A Survey of Large Language Models in Finance (FinLLMs)4 Feb 2024
- 2023FinEntity: Entity-level Sentiment Classification for Financial Texts19 Oct 2023