paper-with-me

홈 › Papers

Investigating the Robustness of Retrieval-Augmented Generation at the Query Level

2025-07-09 · Sezen Perçin, Xin Su, Qutub Sha Syed, Phillip Howard, Aleksei Kuvshinov, Leo Schwinn, Kay-Ulrich Scholl arxiv

Large language models (LLMs) are very costly and inefficient to update with new information. To address this limitation, retrieval-augmented generation (RAG) has been proposed as a solution that dynamically incorporates external knowledge during inference, improving factual consistency and reducing hallucinations. Despite its promise, RAG systems face practical challenges-most notably, a strong dependence on the quality of the input query for accurate retrieval. In this paper, we investigate the sensitivity of different components in the RAG pipeline to various types of query perturbations. Our analysis reveals that the performance of commonly used retrievers can degrade significantly even under minor query variations. We study each module in isolation as well as their combined effect in an end-to-end question answering setting, using both general-domain and domain-specific datasets. Additionally, we propose an evaluation framework to systematically assess the query-level robustness of RAG pipelines and offer actionable recommendations for practitioners based on the results of more than 1092 experiments we performed.

📄 PDF Abstract BibTeX arXiv:2507.06956

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Unveiling the Magic: Investigating Attention Distillation in Retrieval-augmented Generation

2024-02-19 · Zizhong Li, Haopeng Zhang, Jiawei Zhang

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augment…

RetrievalRetrieval-augmented Generation

RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts

2025-10-06 · Yining She, Daniel W. Peterson, Marianne Menglin Liu, Vikas Upadhyay 외 arxiv

With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based guardrail models have emerged as a popular solution to screen unsafe inpu…

Ext2Gen: Alignment through Unified Extraction and Generation for Robust Retrieval-Augmented Generation

2025-02-28 · Hwanjun Song, Jeonghwan Choi, Minseok Kim

Retrieval-augmented generation (RAG) enhances LLMs by integrating external knowledge, but generation remains fragile due to the uncertain placement of relevant chunks and retrieval-induced information overload, leading t…

RAGRetrievalRetrieval-augmented Generation

QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors

2025-04-05 · Kepu Zhang, Zhongxiang Sun, Weijie Yu, Xiaoxue Zang 외

Retriever-augmented generation (RAG) has become a widely adopted approach for enhancing the factual accuracy of large language models (LLMs). While current benchmarks evaluate the performance of RAG methods from various …

Contrastive LearningRAGRetrievalRetrieval-augmented Generation

How You Ask Matters! Adaptive RAG Robustness to Query Variations

2026-04-12 · Yunah Jang, Megha Sundriyal, Kyomin Jung, Meeyoung Cha arxiv

Adaptive Retrieval-Augmented Generation (RAG) promises accuracy and efficiency by dynamically triggering retrieval only when needed and is widely used in practice. However, real-world queries vary in surface form even wi…