Skip to content
World-controllerPublic

About

CEBRA: State-Aware Chunk Reduction for Efficient Context Construction in Multi-Hop RAG

Topics

Resources

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

CEBRA

State-Aware Chunk Reduction for Efficient Context Construction in Multi-Hop RAG

CEBRA constructs compact reader contexts from fixed multi-hop retrieval trajectories. It scores a candidate using the evidence already retained, then applies a calibrated retention policy before downstream answer generation.

  • Coverage-Aware Evidence Scoring (CAES): a nine-feature, class-balanced logistic-regression scorer estimates marginal supporting-evidence contribution.
  • Budget-Aware Operating-point Selection (BAOS): held-out calibration balances evidence preservation and average context size against a budget-only reference.
  • Fixed retrieval, adaptive retention: candidate retrieval and query updates stay unchanged; CEBRA controls which retrieved chunks enter the reader context.

CEBRA framework from the manuscript: frozen upstream retrieval, CAES, BAOS, and test-time evidence retention

CEBRA framework from the manuscript. View the original PDF.

Quick start

Use Python 3.11 in a fresh environment. The example below requires no GPU, LLM weights, API key, or paid inference.

git clone https://github.com/World-controller/CEBRA.git
cd CEBRA
python3.11 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements-cebra.txt

python src/cebra.py retain \
  --config configs/hotpotqa.json \
  --fpath examples/smoke/test.jsonl \
  --output outputs/smoke-retained.jsonl \
  --smoke-example

python src/cebra.py evaluate \
  --fpath outputs/smoke-retained.jsonl \
  --output outputs/smoke-metrics.json

This is a synthetic smoke example, not a benchmark or a claim to reproduce paper results. --smoke-example explicitly uses regex lexical features only on marked synthetic rows. The bundled scorer is unchanged, but these example features are not the formal NLP profile. Output metadata records that distinction. Existing output files are never overwritten; use a new destination when rerunning.

Train, calibrate, retain, evaluate

The public interface is python src/cebra.py <command> --help.

Command Input Output
train Separate training trajectories with supporting-document IDs CAES scorer and provenance sidecar
calibrate Calibration-only trajectories, split manifest, trained scorer BAOS candidate curve and locked operating point
retain Retrieval trajectories and a frozen config or model + lock Compatible JSONL with retention decisions
evaluate Retained trajectories with supporting-document annotations Recall, unique context size, duplicates, empty contexts and schema coverage

For normal NLP features, first install the pinned language model:

python -m pip install -r requirements-nlp.txt

See the reproducibility guide for full commands, split manifests, frozen configurations and the exact BAOS selection behavior. See the trajectory format for input/output fields. The original research entry points remain compatible.

Frozen artifacts

Evaluation dataset Scorer training source Threshold Mode
HotpotQA 2WikiMultiHopQA training trajectories 0.7 base
2WikiMultiHopQA HotpotQA validation-derived trajectories 0.2 base
MuSiQue Same HotpotQA transfer scorer 0.1 base

The two small scorer files are copied unchanged and checked against recorded SHA-256 hashes. These are frozen operating points, not new fits or recalibration. base means no minimum-per-round fallback. The budget reference is B=3; CEBRA is not a hard per-question top-3 selector.

Data and downstream readers

The quick start includes synthetic text only. Full experiments require separately prepared corpus data, split IDs and retrieval trajectories. Source datasets: HotpotQA, 2WikiMultiHopQA, and MuSiQue.

The advanced guide covers trajectory generation, baseline evaluation and reader integration. The paper uses an 8B reader with CUDA and a 70B reader through hosted APIs. Those stages have separate hardware, model-access and service requirements; they are not part of the CPU smoke example. Full datasets, large model weights and complete historical experiment outputs are not bundled in this code release.

Code map

Paper and citation

This repository accompanies CEBRA: State-Aware Chunk Reduction for Efficient Context Construction in Multi-Hop RAG. Bibliographic metadata and a paper link will be added when available; no publication venue, acceptance status or DOI is asserted here. For now, reference this repository URL and the exact commit you use.

License and third-party components

Code is distributed under the MIT license. Existing copyright and license notices are preserved. See third-party acknowledgments and NOTICE for source attribution and model-license requirements. Model and dataset terms apply separately.

Built with Meta Llama 3.

About

CEBRA: State-Aware Chunk Reduction for Efficient Context Construction in Multi-Hop RAG

Topics

Resources

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages