arXiv 2610.29722 · cs.CL · 2026-10-21
Retrieval Augmented Generation Compositionality
Ido Levy, Segev Shlomov, Leshem Choshen
IBM
In latest · #267 Added on 2026-10-24
One-line takeaway
IBM's open-source LASAGNA framework runs controlled RAG evaluation across 450 configurations, eight benchmarks and corpora from 5K to 200K documents, testing whether isolated gains from embedding, chunking, retrieval, reranking, query augmentation, compression and agentic verification survive composition and scale.
IBM 的 LASAGNA 开源框架做受控 RAG 评测：把嵌入、分块、检索、重排、查询扩展、上下文压缩和智能体校验组合起来测，450 种配置、8 个基准、语料从 5K 到 200K 文档，检验单项技术的收益在组合和大规模下是否还成立。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Benchmarks & data
- RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations ▲287
- PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews ▲210
- DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems ▲74
- GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay ▲73
- More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models ▲65
More on LLMs
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.