Is Contriever superseded?

Contriever (Retrieval-augmented generation): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 4 beat it on benchmarks — #45 of 1179 most-superseded. Sub-problem: cluster led by BM25. Newer alternatives in the same sub-problem include Beyond Topical Similarity, Experience-RAG Skill, LFRAG, Don't Retrieve, Navigate, MIGRASCOPE.

Retrieval-augmented generation

Contriever

Superseded baseline#45 of 1,179 most-superseded

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 4 beat it on benchmarks

Beaten on benchmarks

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

CERA beats Contriever
0.2016 vs 0.0214
Recall@1 · [Evidence Inference Dataset 2.0]
Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
FairFilter-Contriever beats Contriever
0.044 vs 0.571
Overall Fairness · [Llama3.2-1b with Contriever]
The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation
CAR beats Contriever
49.042 vs 48.167
NDCG@5 AVG · [Contriever retriever only]
CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation
PURPLE beats Contriever
13.2 vs 13.0
ROUGE-L · [Phi-4-Mini-Instruct (3.84B)]
Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.