홈 › Papers

Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning

2025-06-09 · Anvi Alex Eponon, Moein Shahiki-Tash, Ildar Batyrshin, Christian E. Maldonado-Sifuentes, Grigori Sidorov, Alexander Gelbukh

This study presents a question-based knowledge encoding approach that improves retrieval-augmented generation (RAG) systems without requiring fine-tuning or traditional chunking. We encode textual content using generated questions that span the lexical and semantic space, creating targeted retrieval cues combined with a custom syntactic reranking method. In single-hop retrieval over 109 scientific papers, our approach achieves a Recall@3 of 0.84, outperforming traditional chunking methods by 60 percent. We also introduce "paper-cards", concise paper summaries under 300 characters, which enhance BM25 retrieval, increasing MRR@3 from 0.56 to 0.85 on simplified technical queries. For multihop tasks, our reranking method reaches an F1 score of 0.52 with LLaMA2-Chat-7B on the LongBench 2WikiMultihopQA dataset, surpassing chunking and fine-tuned baselines which score 0.328 and 0.412 respectively. This method eliminates fine-tuning requirements, reduces retrieval latency, enables intuitive question-driven knowledge access, and decreases vector storage demands by 80%, positioning it as a scalable and efficient RAG alternative.

📄 PDF Abstract BibTeX arXiv:2506.13778

Code (0)

등록된 구현이 없습니다.

Tasks

Chunking Question Generation Question-Generation RAGRerankingRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

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.

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…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

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…

Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation

2025-08-13 · Seokgi Lee arxiv

We introduce a novel retrieval-augmented generation (RAG) framework tailored for multihop question answering. First, our system uses large language model (LLM) to decompose complex multihop questions into a sequence of s…

Question Answering

MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries

2024-01-27 · Yixuan Tang, Yi Yang

Retrieval-augmented generation (RAG) augments large language models (LLM) by retrieving relevant knowledge, showing promising potential in mitigating LLM hallucinations and enhancing response quality, thereby facilitatin…

Benchmarking RAG Retrieval Retrieval-augmented Generation

Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge Editing

2025-11-30 · Li Yuan, Qingfei Huang, Bingshan Zhu, Yi Cai 외 arxiv

Multimodal Knowledge Editing (MKE) extends traditional knowledge editing to settings involving both textual and visual modalities. However, existing MKE benchmarks primarily assess final answer correctness while neglecti…

Multimodal Reasoning Question Answering knowledge editing Knowledge Graphs

The Reasoning Bottleneck in Graph-RAG: Structured Prompting and Context Compression for Multi-Hop QA

2026-03-14 · Yasaman Zarrinkia, Venkatesh Srinivasan, Alex Thomo arxiv

Graph-RAG systems achieve strong multi-hop question answering by indexing documents into knowledge graphs, but strong retrieval does not guarantee strong answers. Evaluating KET-RAG, a leading Graph-RAG system, on three …

Multi-hop Question Answering Knowledge Graphs

PROPEX-RAG: Enhanced GraphRAG using Prompt-Driven Prompt Execution

2025-11-03 · Tejas Sarnaik, Manan Shah, Ravi Hegde arxiv

Retrieval-Augmented Generation (RAG) has become a robust framework for enhancing Large Language Models (LLMs) with external knowledge. Recent advances in RAG have investigated graph based retrieval for intricate reasonin…

Multi-hop Question Answering Answer Generation Fact Selection