rmr2024 / finextract
Benchmark and fix LLM hallucinations when extracting figures from SEC 10-K filings
Why this job: says: benchmark; topics: evaluation
What it does
A benchmark and pipeline for extracting financial figures from SEC 10-K filings with LLMs, and for measuring exactly how the extraction fails.
Get started
pip install -e ".[dev]"
pytest
# offline test suite
finextract demo
# whole pipeline on a bundled synthetic filing, no keys or network- Maintenance
- Active
- Last commit 8 days ago
- Stars
- 24
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.0.0
- Released 8 days ago
- Built with
- Python
- 88% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 0 merged
- 0 waiting
- Releases
- 1
- 1 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| georgeguimaraes / tribunal | 119 | 14 days ago | MIT | No downloads |
| strands-agents / evals | 252 | 4 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 88%
- HTML 12%
- Dockerfile 1%
Topics
- evaluation
- fastapi
- finance
- llm
- python
- rag
- sec-edgar
Project record
- JobEvals and observability
- StatusNew to our list
- Commits19
- Forks0
- Watching0
- CreatedOct 31, 2026
- First seen by usNov 7, 2026
- CheckedNov 8, 2026