GARAG (Retrieval-augmented generation): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 1 beat it on benchmarks — #132 of 1179 most-superseded. Sub-problem: cluster led by PoisonedRAG. Newer alternatives in the same sub-problem include DiscourseFlip, SilentRetrieval, Deceptive Evolutionary Jamming Attack (DEJA), LogicPoison, KEPo.

Retrieval-augmented generation

GARAG

Superseded baseline#132 of 1,179 most-superseded

Superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 1 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites GARAG as a baseline.

its scope is limited to plain text using only synthetic data, overlooking the variety of OCR noise encountered in real-world RAG applications.

— OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation

Beaten on benchmarks

Head-to-head results where a newer method reports beating GARAG. Values are copied from the source paper's tables — verify against the cited paper.

TPARAG beats GARAG
98.6 vs 73.3
ASR_T · [White-box (TPARAG) vs White-box (GARAG), NQ dataset, Mistral-7B]
Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.