Is CompAct superseded?

CompAct (Retrieval-augmented generation): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 5 beat it on benchmarks — #37 of 1179 most-superseded.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.

Retrieval-augmented generation

CompAct

CompAct: Compressing Retrieved Documents Actively for Question Answering

Superseded baseline#37 of 1,179 most-superseded · first seen Jul 12, 2024

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 5 beat it on benchmarks

Beaten on benchmarks

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

OkraLong beats CompAct
51.4 vs 30.9
Score · [Average]
OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing
Ext2Gen-R2 beats CompAct
0.463 vs 0.343
Acc · [Llama3.1-8b-instruct backbone]
Aligning Extraction and Generation for Robust Retrieval-Augmented Generation
AttnComp beats CompAct
19.6 vs 16.5
Acc · [MuSiQue]
AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
QREAM-FT beats CompAct
45.6 vs 40.1
Accuracy · [Standard RAG Pipeline with Llama-3-8B-Instruct]
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
Oreo beats CompAct
0.658 vs 0.5974
F1 · [Multi-hop QA with Flan-T5]
Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented 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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.