跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-21AI 評分51

LASAGNA 評估 RAG 組合效果,發現單項技術收益難以預測整體表現

Retrieval Augmented Generation Compositionality

AI 導讀

LASAGNA 研究以開源框架評估不同規模的 RAG 流程,發現單項技術的收益未必能預測組合後的檢索品質、答案忠實度或大語料表現。研究測試 8 個基準上的 450 種配置,涵蓋 5K 至 200K 份文件;三種檢索技術預計組合提升 +47%,實際合用僅提升 +17%。研究亦發現,提升檢索品質與答案忠實度可能需要不同組合,且最佳組合會隨語料規模改變。

正文

Published on Oct 21

Authors:

,

Abstract

LASAGNA evaluates composed RAG pipelines across scales and finds that isolated technique gains do not reliably predict combined retrieval quality, faithfulness, or large-corpus performance.

Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, reranking, query augmentation, context compression, and agentic verification, yet these techniques are typically evaluated one at a time. It remains unclear whether their isolated gains survive composition, whether retrieval quality and answer faithfulness favor the same design choices, and whether conclusions from small corpora hold at large scale. We pre-declare three hypotheses and introduce LASAGNA, an open-source framework for controlled RAG evaluation. We test 450 configurations across eight benchmarks and corpora ranging from 5K to 200K documents. Three findings emerge. First, individually strong techniques from different phases of a RAG pipeline do not necessarily compose: three retrieval techniques predict a +47% combined improvement but deliver only +17% when used together. Second, component gains stack differently for retrieval and faithfulness, and optimizing one can hurt the other. Third, the best composition changes as the corpus grows: the combination that wins on a small corpus may not remain best at large scale. These findings show that gains measured in isolation are not reliable predictors of realistic performance, and that new RAG techniques should be tested with the full surrounding stack. We call on researchers to do so and supply LASAGNA to simplify these experiments.

View arXiv page View PDF Project page GitHub 1 Add to collection

Get this paper in your agent:

hf papers read 2610.29722

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.29722 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.29722 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.29722 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co