paper-with-me

홈 › Papers

Multiple Abstraction Level Retrieve Augment Generation

2025-01-28 · Zheng Zheng, Xinyi Ni, Pengyu Hong

A Retrieval-Augmented Generation (RAG) model powered by a large language model (LLM) provides a faster and more cost-effective solution for adapting to new data and knowledge. It also delivers more specialized responses compared to pre-trained LLMs. However, most existing approaches rely on retrieving prefix-sized chunks as references to support question-answering (Q/A). This approach is often deployed to address information needs at a single level of abstraction, as it struggles to generate answers across multiple levels of abstraction. In an RAG setting, while LLMs can summarize and answer questions effectively when provided with sufficient details, retrieving excessive information often leads to the 'lost in the middle' problem and exceeds token limitations. We propose a novel RAG approach that uses chunks of multiple abstraction levels (MAL), including multi-sentence-level, paragraph-level, section-level, and document-level. The effectiveness of our approach is demonstrated in an under-explored scientific domain of Glycoscience. Compared to traditional single-level RAG approaches, our approach improves AI evaluated answer correctness of Q/A by 25.739\% on Glyco-related papers.

📄 PDF Abstract BibTeX arXiv:2501.16952

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelQuestion AnsweringRAGRetrieval-augmented GenerationSentence

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 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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 $x$…
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.
Adam 설명 없음
Residual Connection 설명 없음
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…

Similar Papers 제목 키워드 기반

Latent Abstraction for Retrieval-Augmented Generation

2026-04-20 · Ha Lan N. T, Minh-Anh Nguyen, Dung D. Le arxiv

Retrieval-Augmented Generation (RAG) has become a standard approach for enhancing large language models (LLMs) with external knowledge, mitigating hallucinations, and improving factuality. However, existing systems rely …

Natural Language Queries

Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation

2026-05-01 · Ziwen Zhao, Menglin Yang arxiv

Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at multiple granularities. However, existin…

Question Answering

Incorporating Q&A Nuggets into Retrieval-Augmented Generation

2026-01-19 · Laura Dietz, Bryan Li, Gabrielle Liu, Jia-Huei Ju 외 arxiv

RAGE systems integrate ideas from automatic evaluation (E) into Retrieval-augmented Generation (RAG). As one such example, we present Crucible, a Nugget-Augmented Generation System that preserves explicit citation proven…

Improving Abstraction in Text Summarization

2018-08-23 · EMNLP 2018 10 · Wojciech Kryściński, Romain Paulus, Caiming Xiong, Richard Socher

Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by nov…

Abstractive Text SummarizationDecoderLanguage ModelingLanguage Modelling+2

Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism

2024-10-11 · Yimin Tang, Yurong Xu, Ning Yan, Masood Mortazavi

Transformers have a quadratic scaling of computational complexity with input size, which limits the input context window size of large language models (LLMs) in both training and inference. Meanwhile, retrieval-augmented…

RAGRetrievalRetrieval-augmented Generation