paper-with-me

Papers

Retrieval augmentation of large language models for lay language generation

2022-11-07 · Yue Guo, Wei Qiu, Gondy Leroy, Sheng Wang, Trevor Cohen

Recent lay language generation systems have used Transformer models trained on a parallel corpus to increase health information accessibility. However, the applicability of these models is constrained by the limited size and topical breadth of available corpora. We introduce CELLS, the largest (63k pairs) and broadest-ranging (12 journals) parallel corpus for lay language generation. The abstract and the corresponding lay language summary are written by domain experts, assuring the quality of our dataset. Furthermore, qualitative evaluation of expert-authored plain language summaries has revealed background explanation as a key strategy to increase accessibility. Such explanation is challenging for neural models to generate because it goes beyond simplification by adding content absent from the source. We derive two specialized paired corpora from CELLS to address key challenges in lay language generation: generating background explanations and simplifying the original abstract. We adopt retrieval-augmented models as an intuitive fit for the task of background explanation generation, and show improvements in summary quality and simplicity while maintaining factual correctness. Taken together, this work presents the first comprehensive study of background explanation for lay language generation, paving the path for disseminating scientific knowledge to a broader audience. CELLS is publicly available at: https://github.com/LinguisticAnomalies/pls_retrieval.

📄 PDF Abstract BibTeX arXiv:2211.03818

Code (1)

linguisticanomalies/pls_retrieval 공식 구현 pytorch

Tasks

Explanation GenerationRetrievalText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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 $x$…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

LaMP: When Large Language Models Meet Personalization

2023-04-22 · Alireza Salemi, Sheshera Mysore, Michael Bendersky, Hamed Zamani

This paper highlights the importance of personalization in large language models and introduces the LaMP benchmark -- a novel benchmark for training and evaluating language models for producing personalized outputs. LaMP…

Language ModelingLanguage ModellingNatural Language UnderstandingRetrieval+3

Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation

2024-04-09 · Alireza Salemi, Surya Kallumadi, Hamed Zamani

This paper studies retrieval-augmented approaches for personalizing large language models (LLMs), which potentially have a substantial impact on various applications and domains. We propose the first attempt to optimize …

Knowledge DistillationLanguage ModelingLanguage ModellingRetrieval

UniRAG: Universal Retrieval Augmentation for Large Vision Language Models

2024-05-16 · Sahel Sharifymoghaddam, Shivani Upadhyay, Wenhu Chen, Jimmy Lin

Recently, Large Vision Language Models (LVLMs) have unlocked many complex use cases that require Multi-Modal (MM) understanding (e.g., image captioning or visual question answering) and MM generation (e.g., text-guided i…

Image CaptioningImage GenerationQuestion AnsweringRetrieval+1

Retrieval meets Long Context Large Language Models

2023-10-04 · Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee 외

Extending the context window of large language models (LLMs) is getting popular recently, while the solution of augmenting LLMs with retrieval has existed for years. The natural questions are: i) Retrieval-augmentation v…

16k4kFew-Shot LearningNatural Questions+2

ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System

2022-05-30 · NAACL (MIA) 2022 7 · Chia-Chien Hung, Tommaso Green, Robert Litschko, Tornike Tsereteli 외

This paper introduces our proposed system for the MIA Shared Task on Cross-lingual Open-retrieval Question Answering (COQA). In this challenging scenario, given an input question the system has to gather evidence documen…

Answer GenerationData AugmentationLanguage ModellingPassage Retrieval+2