maastrichtlawtech/lleqa

🤖 Long-form question answering in the legal domain. (AAAI 2024)

24
/ 100
Experimental

Implements a retrieve-then-read pipeline combining retrieval with large language models to generate detailed, multi-sentence answers grounded in statutory provisions. Introduces LLeQA, a 1,868 expert-annotated French legal QA dataset with full answer chains linked to relevant legal articles, serving as a benchmark for evaluating LLM performance on specialized domain reasoning. Targets interpretability in legal aid systems by connecting generated answers directly to source legal provisions rather than producing unsupported responses.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 9 / 25
Community 7 / 25

How are scores calculated?

Stars

45

Forks

3

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/maastrichtlawtech/lleqa"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.