paper-with-me

Papers

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

2024-10-11 · Zhuoqun Li, Xuanang Chen, Haiyang Yu, Hongyu Lin, Yaojie Lu, Qiaoyu Tang, Fei Huang, Xianpei Han, Le Sun, Yongbin Li

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful information required to these tasks are badly scattered. This characteristic makes it difficult for existing RAG methods to accurately identify key information and perform global reasoning with such noisy augmentation. In this paper, motivated by the cognitive theories that humans convert raw information into various structured knowledge when tackling knowledge-intensive reasoning, we proposes a new framework, StructRAG, which can identify the optimal structure type for the task at hand, reconstruct original documents into this structured format, and infer answers based on the resulting structure. Extensive experiments across various knowledge-intensive tasks show that StructRAG achieves state-of-the-art performance, particularly excelling in challenging scenarios, demonstrating its potential as an effective solution for enhancing LLMs in complex real-world applications.

📄 PDF Abstract BibTeX arXiv:2410.08815

Code (1)

li-z-q/structrag 공식 구현

Tasks

RAGRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
WordPiece 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

2024-06-19 · Zhepei Wei, Wei-Lin Chen, Yu Meng

Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneou…

DenoisingIn-Context LearningRAGRetrieval+1

InstructRAG: Leveraging Retrieval-Augmented Generation on Instruction Graphs for LLM-Based Task Planning

2025-04-17 · Zheng Wang, Shu Xian Teo, Jun Jie Chew, Wei Shi

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, b…

Meta-LearningMeta Reinforcement LearningRAGreinforcement-learning+4

FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG

2026-02-01 · Mengzhu Chen, Haodong Yang, Jia Cai, Xiaolin Huang arxiv

Retrieval-Augmented Generation (RAG) systems critically depend on how external knowledge is segmented, structured, and retrieved. Most existing approaches either retrieve fixed-length text chunks, which fragments discour…

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

2023-05-28 · NeurIPS 2023 11 · Minki Kang, Seanie Lee, Jinheon Baek, Kenji Kawaguchi 외

Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the LLMs in real-world applications can be c…

MedQAMemorizationStrategyQA

Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing

2026-05-11 · Qinghua Mao, Xi Lin, Jinze Gu, Jun Wu 외 arxiv

Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces critical safety risks: adversaries can inject malicious or misleading kno…

knowledge editing