Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
|
| 2 |
|
| 3 |
# ₩ON: Open LLM for Korean Finance
|
| 4 |
|
|
@@ -27,6 +27,15 @@ The benchmark used during the competition consisted of approximately 5,500 caref
|
|
| 27 |
- **Financial Agents**: Tasked models with executing financial data manipulations and coding tasks.
|
| 28 |
- **Open-Ended FinQA**: Comprised of complex graduate-level econometric and legal reasoning tasks.
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
**Benchmark Competition Statistics**
|
| 31 |
|
| 32 |
The competition saw broad participation, with 52.5% corporate teams from sectors such as Tech and Finance, and significant academic involvement, reflecting diverse stakeholder interest in Korean financial NLP.
|
|
@@ -98,15 +107,6 @@ The benchmark is categorized into Finance & Accounting (F&A), Financial Market a
|
|
| 98 |
- **Financial Market Analysis**: It assesses the model's understanding of financial markets, systems, regulations, and domain-specific factual knowledge.
|
| 99 |
- **Open-Ended FinQA**: It comprises complex and detailed reasoning questions to simulate realistic financial problem-solving scenarios.
|
| 100 |
|
| 101 |
-
An example of this evaluation dataset is the following:
|
| 102 |
-
|
| 103 |
-
<figure style="text-align: center;">
|
| 104 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/63e087b6a98d931aa90c1b9c/7vLKeR6wTbr88UdOeikaE.png" width="700" height="900" alt="샘플 이미지" style="display: block; margin: auto;">
|
| 105 |
-
<figcaption style="font-style: italic; color: gray; margin-top: 8px;">
|
| 106 |
-
Overview of the benchmark used for evaluation. Each example demonstrates a specific question type for each category.
|
| 107 |
-
</figcaption>
|
| 108 |
-
</figure>
|
| 109 |
-
|
| 110 |
**Results**
|
| 111 |
|
| 112 |
₩ON emerged as the highest-performing model on average compared to the models awarded in the competition.
|
|
|
|
| 1 |
+
**🇺🇸 English** | [🇰🇷 한국어](https://huggingface.co/KRX-Data/WON-Reasoning/blob/main/KOREAN_README.md)
|
| 2 |
|
| 3 |
# ₩ON: Open LLM for Korean Finance
|
| 4 |
|
|
|
|
| 27 |
- **Financial Agents**: Tasked models with executing financial data manipulations and coding tasks.
|
| 28 |
- **Open-Ended FinQA**: Comprised of complex graduate-level econometric and legal reasoning tasks.
|
| 29 |
|
| 30 |
+
An example of benchmark dataset is the following:
|
| 31 |
+
|
| 32 |
+
<figure style="text-align: center;">
|
| 33 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63e087b6a98d931aa90c1b9c/7vLKeR6wTbr88UdOeikaE.png" width="700" height="900" alt="샘플 이미지" style="display: block; margin: auto;">
|
| 34 |
+
<figcaption style="font-style: italic; color: gray; margin-top: 8px;">
|
| 35 |
+
Overview of the benchmark used for evaluation. Each example demonstrates a specific question type for each category.
|
| 36 |
+
</figcaption>
|
| 37 |
+
</figure>
|
| 38 |
+
|
| 39 |
**Benchmark Competition Statistics**
|
| 40 |
|
| 41 |
The competition saw broad participation, with 52.5% corporate teams from sectors such as Tech and Finance, and significant academic involvement, reflecting diverse stakeholder interest in Korean financial NLP.
|
|
|
|
| 107 |
- **Financial Market Analysis**: It assesses the model's understanding of financial markets, systems, regulations, and domain-specific factual knowledge.
|
| 108 |
- **Open-Ended FinQA**: It comprises complex and detailed reasoning questions to simulate realistic financial problem-solving scenarios.
|
| 109 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
**Results**
|
| 111 |
|
| 112 |
₩ON emerged as the highest-performing model on average compared to the models awarded in the competition.
|