NLP Research
SoPromptTuningforAugmentingDenseRetrievalwithLargeLanguageModelsZhiyuanPeng∗SantaClaraUniversitySantaClaraUSAzpengscueduXuyangWu∗SantaClaraUniversitySantaClaraUSAxwu5scueduY
AugTrieverUnsupervisedDenseRetrievalbyScalableDataAugmentationRuiMengYeLiuSemihYavuzDivyanshAgarwalLifuTuNingYuJianguoZhangMeghanaBhatYingboZhouSalesforceResearchruimen
QuestionsAreAllYouNeedtoTrainaDensePassageRetrieverDevendraSinghSachan12MikeLewis3DaniYogatama4LukeZettlemoyer35JoellePineau123ManzilZaheer41McGillUniversityCanada2M
Task-awareRetrievalwithInstructionsAkariAsai†‡TimoSchick†PatrickLewis†XilunChen†GautierIzacard†♠SebastianRiedel♣HannanehHajishirzi‡♥Wen-tauYih††MetaAI‡UniversityofWashingto
AIOpen4202380–90Availableonline7August20232666-6510©2023TheAuthorsPublishingservicesbyElsevierBVonbehalfofKeAiCommunicationsCoLtdThisisanopenaccessarticleundert
AIOpen4202380–90Availableonline7August20232666-6510©2023TheAuthorsPublishingservicesbyElsevierBVonbehalfofKeAiCommunicationsCoLtdThisisanopenaccessarticleundert
1LargeLanguageModelsforInformationRetrievalASurveyYutaoZhuHuayingYuanShutingWangJiongnanLiuWenhanLiuChenlongDengZhichengDouandJi-RongWenAbstractAsaprimarymeansofinf
REALMRetrieval-AugmentedLanguageModelPre-TrainingKelvinGuu1KentonLee1ZoraTung1PanupongPasupat1Ming-WeiChang1AbstractLanguagemodelpre-traininghasbeenshowntocaptureasurprisingamo
Retrieval-AugmentedGenerationforKnowledge-IntensiveNLPTasksPatrickLewis†‡EthanPerezAleksandraPiktus†FabioPetroni†VladimirKarpukhin†NamanGoyal†HeinrichKüttler†MikeLewis†Wen-