Lite-FLANG-SL: Sequence Labeling for HiFi-KPI Lite

Model Description

Lite-FLANG-SL is a FLANG-based sequence labeling model fine-tuned on the HiFi-KPI Lite dataset for extracting financial key performance indicators (KPIs) from English SEC earnings filings (10-K and 10-Q reports).

The model starts from SALT-NLP/FLANG-BERT, a financial-domain BERT model. It is the FLANG-based counterpart of Lite-BERT-SL in the HiFi-KPI model collection. The dataset and extraction tasks are described in HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings.

It uses the expert-mapped HiFi-KPI Lite label space, covering revenues, earnings, EPS (earnings per share), and EBIT (earnings before interest and taxes), together with outside and out-of-scope labels.

Base model: SALT-NLP/FLANG-BERT
Model architecture: BertForTokenClassification
Task: Token classification (sequence labeling)
Language: English
Dataset: AAU-NLP/hifi-kpi-lite

Use Cases

Extracting financial KPI mentions from SEC 10-K and 10-Q filings.
Financial document parsing with iXBRL-based entity recognition.
Mapping financial mentions to expert-curated KPI categories.

Label Space

The checkpoint has seven output labels: O, revenues, XBRL-OOS, earnings, eps, ebit, specialOOS.

The saved labels use plain entity names rather than BIO prefixes. Predictions are token-level labels; this checkpoint does not itself return structured records containing financial values, dates, or currencies.

Usage

pip install -U transformers torch

from transformers import pipeline

extract_kpis = pipeline(
    "token-classification",
    model="AAU-NLP/Lite-FLANG-SL",
    tokenizer="AAU-NLP/Lite-FLANG-SL",
    aggregation_strategy="none",
)

predictions = extract_kpis("Revenue was $12.5 million for the quarter.")
print(predictions)

The example returns subword-token predictions with labels, scores, and character offsets. Long filings should be split into paragraphs or chunks that fit the model's input window.

Dataset & Code

Paper: HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings
Dataset: HiFi-KPI Lite on Hugging Face
Code: HiFi-KPI GitHub Repository
Base model: SALT-NLP/FLANG-BERT
BERT counterpart: Lite-BERT-SL

Citation

If you use this model or the dataset, please cite:

@inproceedings{aavang-etal-2026-hifi,
    title = "{H}i{F}i-{KPI}: A Dataset for Hierarchical {KPI} Extraction from Earnings Filings",
    author = "Aavang, Rasmus T.  and
      Rizzi, Giovanni  and
      Tjalk-B{\o}ggild, Rasmus  and
      Iolov, Alexandre  and
      Zhang, Mike  and
      Bjerva, Johannes",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://aclanthology.org/2026.lrec-1.30/",
    doi = "10.63317/2nbsp7zzfb3g",
    pages = "441--455",
}

License

This model is licensed under the Apache License, Version 2.0.

AAU-NLP/Lite-FLANG-SL