Top Research Papers on Retrieval Augmented Generation

This paper proposes RAG-end2end, an extension to RAG that can adapt to a domain- specific knowledge base by updating all components of the external knowledge base during training and introduces an auxiliary training signal to inject more domain-specific knowledge.

Evaluating retrieval-augmented generation with a novel evaluation approach, eRAG, where each document in the retrieval list is individually utilized by the large language model within the RAG system, and the downstream performance for each document serves as its relevance label.

Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

This survey comprehensively review existing research studies in RA-LLMs, covering three primary technical perspectives: architectures, training strategies, and applications, and systematically review mainstream relevant work by their architectures, training strategies, and application areas.

Shahul Es, Jithin James, Luis Espinosa Anke, Steven Schockaert. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. 2024.

The size of the dataset and the fact that the questions are derived from real user search queries distinguishes MS MARCO from other well-known publicly available datasets for machine reading comprehension and question-answering.

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong Park. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Retrieval-Augmented Generation (RAG) is a promising approach for mitigating the hallucination of large language models (LLMs). However, existing research lacks rigorous evaluation of the impact of retrieval-augmented generation on different large language models, which make it challenging to identify the potential bottlenecks in the capabilities of RAG for different LLMs. In this paper, we systematically investigate the impact of Retrieval-Augmented Generation on large language models. We analyze the performance of different large language models in 4 fundamental abilities required for RAG, in...

It is shown that generating diverse contexts for a query is beneficial as fusing their results consistently yields better retrieval accuracy, and as sparse and dense representations are often complementary, GAR can be easily combined with DPR to achieve even better performance.

Large Language Models (LLMs) showcase impressive capabilities but encounter challenges like hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the generation, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs' intrinsic knowledge with the vast, dynamic repositories of exte...

Retrieval-augmented generation has raise extensive attention as it is promising to address the limitations of large language models including outdated knowledge and hallucinations. However, retrievers struggle to capture relevance, especially for queries with complex information needs. Recent work has proposed to improve relevance modeling by having large language models actively involved in retrieval, i.e., to guide retrieval with generation. In this paper, we show that strong performance can be achieved by a method we call Iter-RetGen, which synergizes retrieval and generation in an iterativ...

It is argued here that the retrieval component of RAG systems, be it dense or sparse, deserves increased attention from the research community, and accordingly, the first comprehensive and systematic examination of the retrieval strategy of RAG systems is conducted.

It is shown that In-Context RALM that builds on off-the-shelf general purpose retrievers provides surprisingly large LM gains across model sizes and diverse corpora, and that the document retrieval and ranking mechanism can be specialized to the RALm setting to further boost performance.

The use of neural-retrieval-in-the-loop architectures - recently shown to be effective in open-domain QA - is explored for knowledge-grounded dialogue, a task that is arguably more challenging as it requires querying based on complex multi-turn dialogue context and generating conversationally coherent responses.

While LiVersa demonstrated higher accuracy in answering questions related to hepatology - there were some deficiencies due to limitations set by the number of documents used for RAG, the LiVersa prototype is a proof of concept for utilizing RAG to customize LLMs for clinical use cases.

The study highlights that structured guideline reformatting and advanced prompt engineering can enhance the efficacy of LLM integrations to CDSSs for guideline delivery.

The effectiveness of Retrieval-Augmented Language Model pre-training (REALM) is demonstrated by fine-tuning on the challenging task of Open-domain Question Answering (Open-QA) and is found to outperform all previous methods by a significant margin, while also providing qualitative benefits such as interpretability and modularity.

Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Richard James, Mike Lewis, Luke Zettlemoyer, Wen-tau Yih. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Almanac, an LLM framework augmented with retrieval capabilities from curated medical resources for medical guideline and treatment recommendations, showed a significant improvement in performance compared with the standard LLMs across axes of factuality, completeness, user preference, and adversarial safety.

Large Language Models (LLMs) play powerful, black-box readers in the retrieve-then-read pipeline, making remarkable progress in knowledge-intensive tasks. This work introduces a new framework, Rewrite-Retrieve-Read instead of the previous retrieve-then-read for the retrieval-augmented LLMs from the perspective of the query rewriting. Unlike prior studies focusing on adapting either the retriever or the reader, our approach pays attention to the adaptation of the search query itself, for there is inevitably a gap between the input text and the needed knowledge in retrieval. We first prompt an L...

An approach that learns to generate an internet search query based on the context, and then conditions on the search results to finally generate a response, a method that can employ up-to-the-minute relevant information.

A taxonomy of clarification for open-domain search queries is identified by analyzing large-scale query reformulation data sampled from Bing search logs, and supervised and reinforcement learning models for generating clarifying questions learned from weak supervision data are proposed.

Large language models have shown impressive few-shot results on a wide range of tasks. However, when knowledge is key for such results, as is the case for tasks such as question answering and fact checking, massive parameter counts to store knowledge seem to be needed. Retrieval augmented models are known to excel at knowledge intensive tasks without the need for as many parameters, but it is unclear whether they work in few-shot settings. In this work we present Atlas, a carefully designed and pre-trained retrieval augmented language model able to learn knowledge intensive tasks with very few...

A Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos to facilitate video retrieval with complex queries, thereby achieving a better video retrieval performance.

This work introduces a retrieval-augmented LLMs framework for financial sentiment analysis, which includes an instruction-tuned LL Ms module, which ensures LLMs behave as predictors of sentiment labels, and a retrieval -augmentation module which retrieves additional context from reliable external sources.

In the fast-paced realm of digital transformation, businesses are increasingly pressured to innovate and boost efficiency to remain competitive and foster growth. Large Language Models (LLMs) have emerged as game-changers across industries, revolutionizing various sectors by harnessing extensive text data to analyze and generate human-like text. Despite their impressive capabilities, LLMs often encounter challenges when dealing with domain-specific queries, potentially leading to inaccuracies in their outputs. In response, Retrieval-Augmented Generation (RAG) has emerged as a viable solution. ...

A comprehensive and systematic review and analysis of medical image augmentation work are carried out, and the existing limitations of this type of model are discussed and possible research directions are suggested.

The advent of generative AI has sparked apprehension regarding its capacity to replace human workers in many jobs. However, the most significant opportunity for this technology lies in its potential to assist businesses and governments in addressing the challenges associated with democratizing innovation by augmenting human creativity. These challenges include the influx of ideas, the inability of domain experts to embrace novel concepts, the difficulty in refining vague ideas into actionable plans, and the struggle to integrate diverse customer requirements into viable solutions. Generative A...

A novel Retrieve-Copy-Generate network is proposed, where a pluggable video-to-text retriever is constructed to retrieve sentences as hints from the training corpus effectively, and a copy-mechanism generator is introduced to extract expressions from multi-retrieved sentences dynamically.

This paper uses off-the-shelf sensor motes to record and playback interference patterns as well as to generate customizable and repeat-able interference in real-time, and proposes and develops JamLab: a low-cost infrastructure to augment existing sensornet testbeds with accurate interference generation while limiting the overhead to a simple upload of the appropriate software.

This study shows that using GANs for EEG augmentation can significantly improve BCI performance, especially in real-life applications, whereby users' attention may be diverted.

A method to generate realistic scRNA-seq data using GANs that learn gene expression dependencies from complex samples, and shows that augmenting spare cell populations improves downstream analyses.

In agricultural image analysis, optimal model performance is keenly pursued for better fulfilling visual recognition tasks (e.g., image classification, segmentation, object detection and localization), in the presence of challenges with biological variability and unstructured environments. Large-scale, balanced and ground-truthed image datasets are tremendously beneficial but most often difficult to obtain to fuel the development of highly performant models. As artificial intelligence through deep learning is impacting analysis and modeling of agricultural images, image augmentation plays a cr...

The current skin electronics are summarized as one of the most promising device solutions for future VR/AR devices, especially focusing on the recent materials and structures.

To generate high quality synthetic data for low-resource tagging tasks, a novel augmentation method with language models trained on the linearized labeled sentences is proposed that can consistently outperform the baselines.

A novel knowledge graph augmented pre-trained language generation model KG-BART is proposed, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output and can leverage the graph attention to aggregate the rich concept semantics that enhances the model generalization on unseen concept sets.

This paper proposes a masked sequence-to-sequence method for conditional augmentation of aspect term extraction that is controllable and allows to generate more diversified sentences, and effectively boosts the performances of several current models for aspect terms extraction.

The experimental results demonstrate that the proposed data augmentation methods based on generative models outperform the existingData augmentation approaches such as conditional VAE, Gaussian noise, and rotational data augmented.

The mechanism of how the oxygen deficiency enhanced the sonodynamic efficacy of zinc oxide is revealed, providing a new application of defect engineering in the field of cancer therapy.

The extensive experimental results show that the proposed ARShadowGAN is capable of directly generating plausible virtual object shadows in single light scenes.