Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 

Repository files navigation

ADvisor

✨ Official implementation of ADvisor, proposed in the ACL 2026 Industry Track paper:

Pre-Deployment Advertisement Ranking under Data Scarcity via Context-Aware Criteria Generation with VLMs

ACL Paper Python

🚀 Quick Start

🔗 Using Similar Brand Information

python main.py --use_cross_brand_for_features

🎯 Using Only Target Brand Information

python main.py

Data Format

The expected directory structure is as follows:

data/
├── train_<brand_id>.csv
├── test_<brand_id>.csv
├── caption_dict.json
├── caption_embeddings.pkl
├── brand_embeddings.pkl
└── brand_descriptions.json

Each train_<brand_id>.csv and test_<brand_id>.csv file should contain advertisement-level information and target metric columns used for ranking.

Example:

train_brandA.csv
test_brandA.csv
train_brandB.csv
test_brandB.csv

Optional files such as captions, caption embeddings, brand embeddings, and brand descriptions can be used to provide additional context for VLM-based criteria generation and scoring.

About

Official code repository for "Pre-Deployment Advertisement Ranking under Data Scarcity via Context-Aware Criteria Generation with VLMs" (ACL 2026 Industry Track Oral)

Resources

Stars

6 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages