xRAG (Retrieval-augmented generation): superseded — cited as a baseline and beaten by newer methods. 3 paper(s) critique it, 1 beat it on benchmarks — #58 of 1179 most-superseded. Sub-problem: cluster led by RECOMP. Newer alternatives in the same sub-problem include Bottleneck Attention Intervention for Recovery (BAIR), QREAM, CoCR-RAG, XProvence, Crucible.

Method Drift›Retrieval-augmented generation

Superseded baseline#58 of 1,179 most-superseded

xRAG

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token

Retrieval-augmented generation · first seen May 22, 2024

superseded — cited as a baseline and beaten by newer methods

3 papers critique it · 1 beat it on benchmarks

What papers say

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

“compressing all content into a single token representation ... the compact latent representation discards explicit links to source documents, making citation grounding difficult and the pipeline opaque to developers.”
— Incorporating Q&A Nuggets into Retrieval-Augmented Generation
“As the original xRAG model uses one token to encode an entire passage, which can lead to hallucinations”
— SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
“Nevertheless, such soft approaches often lack interpretability and transferability, and degrade task performance.”
— CORE-RAG: Lossless Compression for Retrieval-Augmented LLMs via Reinforcement Learning

Beaten on benchmarks

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

SARA-EMB beats xRAG · F1 [mixed models]
40.55 vs 32.36
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
SARA-CSI beats xRAG · F1 [mixed models]
85.08 vs 43.36
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.