paper-with-me

홈 › Papers

Can we Evaluate RAGs with Synthetic Data?

2025-08-15 · Jonas van Elburg, Peter van der Putten, Maarten Marx arxiv

We investigate whether synthetic question-answer (QA) data generated by large language models (LLMs) can serve as an effective proxy for human-labeled benchmarks when the latter is unavailable. We assess the reliability of synthetic benchmarks across two experiments: one varying retriever parameters while keeping the generator fixed, and another varying the generator with fixed retriever parameters. Across four datasets, of which two open-domain and two proprietary, we find that synthetic benchmarks reliably rank the RAGs varying in terms of retriever configuration, aligning well with human-labeled benchmark baselines. However, they do not consistently produce reliable RAG rankings when comparing generator architectures. The breakdown possibly arises from a combination of task mismatch between the synthetic and human benchmarks, and stylistic bias favoring certain generators.

📄 PDF Abstract BibTeX arXiv:2508.11758

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RAGSynth: Synthetic Data for Robust and Faithful RAG Component Optimization

2025-05-16 · Haiyang Shen, Hang Yan, Zhongshi Xing, Mugeng Liu 외

RAG can enhance the performance of LLMs on knowledge-intensive tasks. Various RAG paradigms, including vanilla, planning-based, and iterative RAG, are built upon 2 cores: the retriever, which should robustly select relev…

RAGSynthetic Data Generation

Relation-aware graph structure embedding with co-contrastive learning for drug-drug interaction prediction

2023-07-04 · Mengying Jiang, Guizhong Liu, Biao Zhao, Yuanchao Su 외

Relation-aware graph structure embedding is promising for predicting multi-relational drug-drug interactions (DDIs). Typically, most existing methods begin by constructing a multi-relational DDI graph and then learning r…

AttributeContrastive LearningRelation

DragAPart: Learning a Part-Level Motion Prior for Articulated Objects

2024-03-22 · Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi

We introduce DragAPart, a method that, given an image and a set of drags as input, generates a new image of the same object that responds to the action of the drags. Differently from prior works that focused on repositio…

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models

2025-01-09 · Peizhuo Lv, Mengjie Sun, Hao Wang, XiaoFeng Wang 외

In recent years, tremendous success has been witnessed in Retrieval-Augmented Generation (RAG), widely used to enhance Large Language Models (LLMs) in domain-specific, knowledge-intensive, and privacy-sensitive tasks. Ho…

RAGRetrieval-augmented Generation

Introducing Super RAGs in Mistral 8x7B-v1

2024-04-13 · Ayush Thakur, Raghav Gupta

The relentless pursuit of enhancing Large Language Models (LLMs) has led to the advent of Super Retrieval-Augmented Generation (Super RAGs), a novel approach designed to elevate the performance of LLMs by integrating ext…

RetrievalRetrieval-augmented Generation