rLLM

rLLM-FinQA-4B

README

License: apache-2.0

FinQA Overview

FinQA is a financial question-answering agent fine-tuned from Qwen3-4B-Instruct-2507 using reinforcement learning (RL). The model answers questions about SEC 10-K financial statements using specialized tools (SQL queries, table lookup, calculators), achieving 59.70% accuracy on Snorkel Finance Benchmark and 26.6% on Snorkel Finance Reasoning.

Data

Our training dataset is built from SEC 10-K filings and consists of 5,110 question-answer pairs across:

207 companies spanning multiple sectors
6,923 financial tables extracted from 10-K filings
Single-table questions: Direct lookups and calculations from individual tables
Multi-table questions: Cross-table reasoning requiring data from multiple sources

The dataset is available on HuggingFace.

Tools

The agent uses 4 specialized tools for financial analysis:

Table with columns: Tool, Description
Tool	Description
`get_table_names`	List available tables for a given company
`get_table_info`	Get table metadata, columns, dtypes, and sample values
`sql_query`	Execute SQL queries on financial tables (SQLite)
`calculator`	Evaluate mathematical expressions

Training

We fine-tune Qwen3-4B-Instruct-2507 using GRPO with LLM-as-judge rewards for correctness evaluation. A more detailed description of the training recipe can be found in our documentation.

Evaluation

Table with columns: Model, FinQA, FinQA Reasoning
Model	FinQA	FinQA Reasoning
Qwen3-4B-Instruct-2507 (Base)	27.90%	13.90%
gpt-5-nano-2025-08-07	50.00%	26.60%
Qwen3-235B-A22B	51.37%	18.90%
rLLM-FinQA-4B (Ours)	59.70%	26.60%
Gemini-2.5-Pro-Preview	60.60%	34.60%
GPT-4.1-2025-04-14

Serving FinQA

Start a vLLM server and run the agent:

bash
python -m vllm.entrypoints.openai.api_server \
    --model rLLM/rLLM-FinQA-4B \
    --host 0.0.0.0 \
    --port 30000 \
    --dtype bfloat16

python -m projects.finqa.run_finqa

For detailed setup instructions, see the project README.

Acknowledgement

This is a joint collaboration between the rLLM team at UC Berkeley and Snorkel AI.
Our model is trained on top of Qwen3-4B-Instruct-2507.
Our work is done as part of Berkeley Sky Computing Lab.

Citation

bibtex
@misc{rllm2026finqa,
  title={FinQA: Training Financial Agents with Reinforcement Learning},
  author={Manan Roongta and Sijun Tan and Bhavishya Pohani and Charles Dickens and Christopher Glaze},
  year={2026},
  howpublished={\url{https://rllm-project.com/post.html?post=finqa.md}},
  note={Blog Post}
}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

rLLM

Model Tree

Base

Qwen/Qwen3-4B-Instruct-2507

Fine-tuned

this model

Input Modalities

Text

Output Modalities