# Model Card for ChronoBERT

## Model Details

### Model Description

ChronoBERT is a series **high-performance chronologically consistent large language models (LLM)** designed to eliminate lookahead bias and training leakage while maintain good language understanding in time-sensitive applications. The model is pretrained on **diverse, high-quality, open-source, and timestamped text** to maintain chronological consistency.

All models in the series achieve **GLUE benchmark scores that surpass standard BERT.** This approach preserves the integrity of historical analysis and enables more reliable economic and financial modeling.

- **Developed by:** Songrun He, Linying Lv, Asaf Manela, Jimmy Wu
- **Model type:** Transformer-based bidirectional encoder (ModernBERT architecture)
- **Language(s) (NLP):** English
- **License:** MIT License

### Model Sources

- **Paper:** "Chronologically Consistent Large Language Models" (He, Lv, Manela, Wu, 2025)

## How to Get Started with the Model

```python
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("manelalab/chronobert-v1-19991231")
model = AutoModel.from_pretrained("manelalab/chronobert-v1-19991231")

text = "You've gotta be very careful not to mess with the space-time continuum. -- Dr. Brown, Back to the Future"

inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
```

## Training Details

### Training Data

- **Pretraining corpus:** Our initial model $\text{ChronoBERT}_{1999}$ is pretrained on 460 billion tokens of pre-2000, diverse, high-quality, and open-source text data to ensure no leakage of data afterwards.
- **Incremental updates:** Yearly updates from 2000 to 2024 with an additional 65 billion tokens of timestamped text.

### Training Procedure

- **Architecture:** ModernBERT-based model with rotary embeddings and flash attention.
- **Objective:** Masked token prediction.

## Evaluation

### Testing Data, Factors & Metrics

- **Language understanding:** Evaluated on **GLUE benchmark** tasks.
- **Financial forecasting:** Evaluated using **return prediction task** based on Dow Jones Newswire data.
- **Comparison models:** ChronoBERT was benchmarked against **BERT, FinBERT, StoriesLM-v1-1963, and Llama 3.1**.

### Results

- **GLUE Score:** $\text{ChronoBERT}_{1999}$ and $\text{ChronoBERT}_{2024}$ achieved GLUE score of 84.71 and 85.54 respectively, outperforming BERT (84.52).
- **Stock return predictions:** During the sample from 2008-01 to 2023-07, $\text{ChronoBERT}_{\text{Realtime}}$ achieves a long-short portfolio **Sharpe ratio of 4.80**, outperforming BERT, FinBERT, and StoriesLM-v1-1963, and comparable to **Llama 3.1 8B (4.90)**.


## Citation

```
@article{He2025ChronoBERT,
  title={Chronologically Consistent Large Language Models},
  author={He, Songrun and Lv, Linying and Manela, Asaf and Wu, Jimmy},
  journal={Working Paper},
  year={2025}
}
```

## Model Card Authors

- Songrun He (Washington University in St. Louis, h.songrun@wustl.edu)
- Linying Lv (Washington University in St. Louis, llyu@wustl.edu)
- Asaf Manela (Washington University in St. Louis, amanela@wustl.edu)
- Jimmy Wu (Washington University in St. Louis, jimmywu@wustl.edu)