adobe-research/NoLiMa

Official repository for "NoLiMa: Long-Context Evaluation Beyond Literal Matching"

40
/ 100
Emerging

NoLiMa helps evaluate how well large language models (LLMs) can find specific, relevant information buried deep within very long documents, even when the question doesn't use the exact same words as the answer. It takes a question and a lengthy text document as input and measures the model's ability to extract the correct answer, providing a score for different document lengths. This tool is designed for AI researchers and practitioners who are developing or comparing long-context LLMs.

186 stars. No commits in the last 6 months.

Use this if you need to rigorously test whether a large language model can truly understand and retrieve information from extremely long texts, especially when it requires inferring meaning beyond simple keyword matching.

Not ideal if you are looking for an off-the-shelf solution for short-context question answering, or if your primary concern is literal keyword matching performance in information retrieval.

large-language-models LLM-evaluation long-context-AI information-retrieval AI-benchmarking
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

186

Forks

16

Language

Python

License

Last pushed

Jul 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/adobe-research/NoLiMa"

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