Method Drift›Retrieval-augmented generation
RECOMP
RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective AugmentationRetrieval-augmented generation · first seen Oct 6, 2023
superseded — cited as a baseline and beaten by newer methods
6 papers critique it · 12 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites RECOMP as a baseline.
“they rely exclusively on post-retrieval context compression without improving initial retrieval quality, creating an inherent performance ceiling”
— MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG“A critical limitation of these methods is their dependence on fixed compression ratios.”
— AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation“their approach still requires additional models to summarise the retrieved documents”
— Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations“Prior context pruning approaches such as RECOMP~xu2023recomp or DSLR~hwang2024dslr encode sentences in a passage independently of each other. In contrast, Provence encodes all the sentences in a retrieved passage together with a query, in a single reranker forward pass.”
— XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation“CASC consistently outperforms strong baselines, including standard Top-K RAG, and existing context compression methods like RECOMP fangyuan2024recomp and LLMLingua huiqiang2023llmlin, across various Reader LLM backbones”
— Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains“the pre-processing methods introduce additional computational costs during inference and may lead to the loss of essential information.”
— R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation
Beaten on benchmarks
Head-to-head results where a newer method reports beating RECOMP. Values are copied from the source paper's tables — verify against the cited paper.
- RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts
RankCoT beats RECOMP · Avg. [full evaluation]
54.93 vs 48.29
- AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
AttnComp beats RECOMP · Acc [HotpotQA]
45.2 vs 37.5
- AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
AttnComp beats RECOMP · Acc [2WikiMQA]
38.1 vs 30.1
- AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
AttnComp beats RECOMP · Acc [MuSiQue]
19.6 vs 14.5
- AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
AttnComp beats RECOMP · Acc [NQ]
53.0 vs 48.7
- AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
AttnComp beats RECOMP · Acc [PopQA]
65.1 vs 51.8
- AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
AttnComp beats RECOMP · Acc [AVG]
44.2 vs 36.5
- Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
QREAM-FT beats RECOMP · Accuracy [Standard RAG Pipeline with Llama-3-8B-Instruct]
45.6 vs 40.6
- Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
QREAM-FT beats RECOMP · Accuracy [Standard RAG Pipeline with Mistral-7B-Instruct]
44.9 vs 40.4
- Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains
CASC beats RECOMP · F1-score [Llama-3-70B]
65.15 vs 63.20
- Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains
CASC beats RECOMP · F1-score [Llama-3-8B]
56.12 vs 55.45
- Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains
CASC beats RECOMP · F1-score [GPT-4o]
65.80 vs 60.55
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.
- Bottleneck Attention Intervention for Recovery (BAIR)The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented GenerationMay 7, 2026
- QREAMAlign Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented GenerationApr 19, 2026
- CoCR-RAGCoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context ReconstructionMar 25, 2026
- Jan 26, 2026
- Jan 19, 2026
- Sep 22, 2025
- Contextual Influence Value (CI value)Influence Guided Context Selection for Effective Retrieval-Augmented GenerationSep 21, 2025