gpl
Unsupervised domain adaptation method for dense retrieval using generative pseudo labeling
GraphCanon updated 2d · GitHub synced 2d
Decision brief
GPL enhances dense retrieval models by adapting them to new domains without the need for labeled data, relying solely on unlabeled corpora.
Good fit when
- When you have an abundance of unlabeled data from a target domain but lack labeled data.
- For improving information retrieval systems where labeling is costly or time-consuming.
Avoid when
- Avoid when high precision and recall on labeled datasets are critical in the initial phase without adaptation.
- If significant computational resources for unsupervised learning are not available, then GPL may not be suitable.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (1144d since push)
- As of 2d
- Provenance
- Not a fork · Organization account
- As of 2d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install gplSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
GPL technique to adapt dense retrieval models through unlabeled data, enhancing performance in new domains without labeled data.
Capability facts
- Languages
- python
Source: github.language · Aug 23, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
Installation
One can either install GPL via pip
pip install gpl
or via git clone
git clone https://github.com/UKPLab/gpl.git && cd gpl
pip install -e .
Meanwhile, please make sure the correct version of PyTorch has been installed according to your CUDA version.
For agents
This page has a .md twin and JSON over the API.