AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation

Zhehao Tan, Yihan Jiao, Dan Yang, Junwei Liu, Lei Liu, Jie Feng, Duolin Sun, Yue Shen, Jian Wang, Peng Wei, Jinjie Gu

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace weak-only noise with harder noise mix (1:3:1) (ablation)Qwen2.5 7B · PRGB Filtering-zhaccuracy: 95.33 -> 80.83Hurt
replace weak-only noise with harder noise mix (1:3:1) (ablation)Qwen2.5 72B · PRGB Filtering-zhaccuracy: 95.58 -> 92.92Hurt
replace weak-only noise with harder noise mix (1:3:1) (ablation)Qwen2.5 7B · PRGB Filtering-enaccuracy: 89.01 -> 84.72Hurt
replace weak-only noise with harder noise mix (1:3:1) (ablation)Qwen2.5 72B · PRGB Filtering-enaccuracy: 89.09 -> 87.42Hurt
enable thinking modeQwen3-235B-A22B · PRGB ZH Overallaccuracy: 75.20 -> 80.76Improved
enable thinking modeQwen3-30B-A3B · PRGB ZH Overallaccuracy: 71.05 -> 80.45Improved
enable thinking modeQwen3-235B-A22B · PRGB EN Overallaccuracy: 70.27 -> 78.68Improved
enable thinking modeQwen3-8B · PRGB ZH Overallaccuracy: 50.02 -> 63.04Improved
scale model from 7B to MAXQwen2.5 · PRGB Combination L3accuracy: 28.60 -> 75.20Improved
scale model from 7B to MAXQwen2.5 · PRGB Combination L1accuracy: 74.07 -> 86.53Improved
scale model from 7B to MAXQwen2.5 · PRGB Reference Reasoning Overallaccuracy: 26.92 -> 55.37Improved
scale model from 32B to 72BQwen2.5 · PRGB Reference Reasoning Overallaccuracy: 44.60 -> 44.14No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy