Skip to content
@project-cera

Project CERA

CERA Logo

Context-Engineered Reviews Architecture
A training-free framework for generating realistic, controllable synthetic review datasets for Aspect-Based Sentiment Analysis (ABSA).


CERA is a modular three-phase pipeline (Composition, Generation, Evaluation) that produces high-quality synthetic ABSA data using only context engineering and multi-agent verification — no GPU infrastructure, fine-tuning, or pre-existing embeddings required.

Developed as part of an MSc thesis at the University of Windsor.

Repositories

Repository Description
cera Core framework — CLI, web GUI, and the full generation pipeline
cera-LADy Latent Aspect Detection evaluation framework for benchmarking generated datasets
cera-human-eval Human evaluation interface for assessing synthetic review quality
cera-vLLM Self-hosted local LLM server for GPU-accelerated generation

Citation

@mastersthesis{thang2026cera,
  title     = {CERA: Context-Engineered Reviews Architecture for
               Synthetic ABSA Dataset Generation},
  author    = {Thang, Kap},
  school    = {University of Windsor},
  year      = {2026},
  type      = {Master's Thesis}
}

Popular repositories Loading

  1. cera cera Public

    CERA: Context-Enriched Review Augmentation

    TypeScript

  2. cera-LADy cera-LADy Public

    CERA-LADy: CERA modified version of LADy baselines

    Python

  3. cera-vLLM cera-vLLM Public

    Self-hosted vLLM server with management dashboard for CERA

    Python

  4. cera-human-eval cera-human-eval Public

    Human evaluation web app for the CERA conference paper (Canadian AI 2026)

    TypeScript

  5. .github .github Public

Repositories

Showing 5 of 5 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…