Given the original question + extracted useful tokens, the Filter selects which tokens to keep in the next retrieval query. This is extractive (no generation) — it picks words from the input.

Architecture

Base: microsoft/mdeberta-v3-base (86M params, multilingual)
Standard DebertaV2ForTokenClassification with 2 labels (keep/discard)

Training


Data	5,691 samples (HotpotQA EN + Dragon-derec RU)
Epochs	2
Batch size	4
LR	1e-5
Max length	128
Hardware	Apple M3 Pro, ~17 minutes

Usage

Training data: Necent/efficientrag-filter-training-data
Labeler model: Necent/efficientrag-labeler-mdeberta-v3-base
Paper: EfficientRAG (arXiv:2408.04259)

Necent/efficientrag-filter-mdeberta-v3-base

EfficientRAG Filter (mdeberta-v3-base)

What it does

Architecture

Training

Usage

Related

Necent/
efficientrag-filter-mdeberta-v3-base