{"total":92,"rows":[{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216,"area":null},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602,"area":null},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452,"area":"rag"},{"id":"2303.13408","title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","created":"2023-03-23","cited_by_count":429,"area":"safety"},{"id":"2203.08913","title":"Memorizing Transformers","created":"2022-03-16","cited_by_count":226,"area":null},{"id":"2103.06332","title":"Hurdles to Progress in Long-form Question Answering","created":"2021-03-10","cited_by_count":167,"area":null},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158,"area":"rag"},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146,"area":null},{"id":"2102.00894","title":"Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models","created":"2021-02-01","cited_by_count":132,"area":null},{"id":"2210.02627","title":"Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering","created":"2022-10-06","cited_by_count":127,"area":"rag"},{"id":"2102.08473","title":"COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining","created":"2021-02-16","cited_by_count":126,"area":null},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125,"area":"mllm"},{"id":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89,"area":null},{"id":"2104.06486","title":"MS2: Multi-Document Summarization of Medical Studies","created":"2021-04-13","cited_by_count":80,"area":null},{"id":"2310.10638","title":"In-context Pretraining: Language Modeling Beyond Document Boundaries","created":"2023-10-16","cited_by_count":79,"area":null},{"id":"2101.00408","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","created":"2021-01-02","cited_by_count":75,"area":null},{"id":"2105.11269","title":"Neural Machine Translation with Monolingual Translation Memory","created":"2021-05-24","cited_by_count":61,"area":null},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2101.00133","title":"NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned","created":"2021-01-01","cited_by_count":52,"area":null},{"id":"2403.13799","title":"Reverse Training to Nurse the Reversal Curse","created":"2024-03-20","cited_by_count":49,"area":null},{"id":"2110.06176","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","created":"2021-10-12","cited_by_count":43,"area":null},{"id":"2101.00178","title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","created":"2021-01-01","cited_by_count":42,"area":null},{"id":"2205.11081","title":"BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla","created":"2022-05-23","cited_by_count":42,"area":null},{"id":"2112.08804","title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs","created":"2021-12-16","cited_by_count":39,"area":null},{"id":"2105.14528","title":"Fast Nearest Neighbor Machine Translation","created":"2021-05-30","cited_by_count":37,"area":null},{"id":"2105.00816","title":"What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization","created":"2021-04-12","cited_by_count":35,"area":null},{"id":"2108.02340","title":"Robust Transfer Learning with Pretrained Language Models through Adapters","created":"2021-08-05","cited_by_count":35,"area":null},{"id":"2110.04541","title":"The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design","created":"2021-10-09","cited_by_count":33,"area":null},{"id":"2507.18910","title":"A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions","created":"2025-07-25","cited_by_count":31,"area":"rag"},{"id":"2207.03637","title":"OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering","created":"2022-07-08","cited_by_count":29,"area":null},{"id":"2403.05676","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","created":"2024-03-08","cited_by_count":28,"area":"rag"},{"id":"2110.08743","title":"GNN-LM: Language Modeling based on Global Contexts via GNN","created":"2021-10-17","cited_by_count":27,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2109.04325","title":"Learning Opinion Summarizers by Selecting Informative Reviews","created":"2021-09-09","cited_by_count":25,"area":null},{"id":"2405.16178","title":"Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection","created":"2024-05-25","cited_by_count":25,"area":"rag"},{"id":"2411.05277","title":"Revisiting the Robustness of Watermarking to Paraphrasing Attacks","created":"2024-11-08","cited_by_count":25,"area":null},{"id":"2210.05758","title":"Decoupled Context Processing for Context Augmented Language Modeling","created":"2022-10-11","cited_by_count":24,"area":null},{"id":"2106.01597","title":"ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation","created":"2021-06-03","cited_by_count":23,"area":null},{"id":"2310.09949","title":"Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models","created":"2023-10-15","cited_by_count":23,"area":"rag"},{"id":"2103.11263","title":"Self-Supervised Test-Time Learning for Reading Comprehension","created":"2021-03-20","cited_by_count":22,"area":null},{"id":"2105.06597","title":"RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling","created":"2021-05-14","cited_by_count":22,"area":"moe"},{"id":"2401.02452","title":"The Compute Divide in Machine Learning: A Threat to Academic Contribution and Scrutiny?","created":"2024-01-04","cited_by_count":20,"area":null},{"id":"2205.14912","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2503.14649","title":"RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving","created":"2025-03-18","cited_by_count":19,"area":"rag"},{"id":"2211.16349","title":"BARTSmiles: Generative Masked Language Models for Molecular Representations","created":"2022-11-29","cited_by_count":18,"area":null},{"id":"2101.00406","title":"CDLM: Cross-Document Language Modeling","created":"2021-01-02","cited_by_count":17,"area":null},{"id":"2110.02600","title":"Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning","created":"2021-10-06","cited_by_count":16,"area":null},{"id":"2109.10410","title":"RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing","created":"2021-09-21","cited_by_count":15,"area":"rag"},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2502.15208","title":"Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing","created":"2025-02-21","cited_by_count":15,"area":null},{"id":"2109.08780","title":"Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy","created":"2021-09-17","cited_by_count":14,"area":null},{"id":"2101.00416","title":"Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting","created":"2021-01-02","cited_by_count":13,"area":null},{"id":"2109.00363","title":"ConRPG: Paraphrase Generation using Contexts as Regularizer","created":"2021-09-01","cited_by_count":13,"area":null},{"id":"2104.07094","title":"Static Embeddings as Efficient Knowledge Bases?","created":"2021-04-14","cited_by_count":11,"area":null},{"id":"2106.07055","title":"GenSF: Simultaneous Adaptation of Generative Pre-trained Models and Slot Filling","created":"2021-06-13","cited_by_count":11,"area":null},{"id":"2204.08123","title":"Non-Parallel Text Style Transfer with Self-Parallel Supervision","created":"2022-04-18","cited_by_count":11,"area":null},{"id":"2103.10334","title":"Structure Inducing Pre-Training","created":"2021-03-18","cited_by_count":10,"area":null},{"id":"2106.07352","title":"MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network","created":"2021-06-02","cited_by_count":10,"area":null},{"id":"2106.02017","title":"A Dataset and Baselines for Multilingual Reply Suggestion","created":"2021-06-03","cited_by_count":9,"area":null},{"id":"2112.08152","title":"Faster Nearest Neighbor Machine Translation","created":"2021-12-15","cited_by_count":8,"area":null},{"id":"2112.08709","title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models","created":"2021-12-16","cited_by_count":8,"area":null},{"id":"2401.04348","title":"LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training","created":"2024-01-09","cited_by_count":8,"area":null},{"id":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2203.17103","title":"$k$NN-NER: Named Entity Recognition with Nearest Neighbor Search","created":"2022-03-31","cited_by_count":6,"area":"rag"},{"id":"2512.06797","title":"Optimal and Diffusion Transports in Machine Learning","created":"2025-12-07","cited_by_count":6,"area":null},{"id":"2108.00356","title":"Improving Social Meaning Detection with Pragmatic Masking and Surrogate Fine-Tuning","created":"2021-08-01","cited_by_count":5,"area":null},{"id":"2210.10820","title":"VTC: Improving Video-Text Retrieval with User Comments","created":"2022-10-19","cited_by_count":5,"area":null},{"id":"2101.08248","title":"Data-to-text Generation by Splicing Together Nearest Neighbors","created":"2021-01-20","cited_by_count":4,"area":null},{"id":"2106.03983","title":"Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2203.10250","title":"Meta-X$_{NLG}$: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation","created":"2022-03-19","cited_by_count":4,"area":null},{"id":"2106.05365","title":"DESCGEN: A Distantly Supervised Dataset for Generating Abstractive Entity Descriptions","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2106.05634","title":"Exploring Unsupervised Pretraining Objectives for Machine Translation","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2205.08605","title":"OneAligner: Zero-shot Cross-lingual Transfer with One Rich-Resource Language Pair for Low-Resource Sentence Retrieval","created":"2022-05-17","cited_by_count":3,"area":null},{"id":"2212.02017","title":"GNN-SL: Sequence Labeling Based on Nearest Examples via GNN","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2305.11564","title":"Decouple knowledge from parameters for plug-and-play language modeling","created":"2023-05-19","cited_by_count":3,"area":null},{"id":"2505.24715","title":"CoRet: Improved Retriever for Code Editing","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2509.25459","title":"SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA","created":"2025-09-29","cited_by_count":3,"area":"rag"},{"id":"2112.08637","title":"Analyzing the Limits of Self-Supervision in Handling Bias in Language","created":"2021-12-16","cited_by_count":2,"area":null},{"id":"2212.07752","title":"Advancing Multilingual Pre-training: TRIP Triangular Document-level Pre-training for Multilingual Language Models","created":"2022-12-15","cited_by_count":2,"area":null},{"id":"2412.17111","title":"Learning to Adapt to Low-Resource Paraphrase Generation","created":"2024-12-22","cited_by_count":2,"area":null},{"id":"2504.21677","title":"20min-XD: A Comparable Corpus of Swiss News Articles","created":"2025-04-30","cited_by_count":2,"area":null},{"id":"2105.03791","title":"Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning","created":"2021-05-08","cited_by_count":1,"area":null},{"id":"2204.13512","title":"Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization","created":"2022-04-28","cited_by_count":1,"area":null},{"id":"2205.04050","title":"Few-shot Mining of Naturally Occurring Inputs and Outputs","created":"2022-05-09","cited_by_count":1,"area":null},{"id":"2206.00362","title":"An Empirical Study of Retrieval-enhanced Graph Neural Networks","created":"2022-06-01","cited_by_count":1,"area":null},{"id":"2304.13559","title":"Towards Multi-Modal DBMSs for Seamless Querying of Texts and Tables","created":"2023-04-26","cited_by_count":1,"area":null},{"id":"2103.11011","title":"Let Your Heart Speak in its Mother Tongue: Multilingual Captioning of Cardiac Signals","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2104.05928","title":"Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoders","created":"2021-04-13","cited_by_count":0,"area":null},{"id":"2108.11992","title":"Enhanced Seq2Seq Autoencoder via Contrastive Learning for Abstractive Text Summarization","created":"2021-08-26","cited_by_count":0,"area":null},{"id":"2209.13940","title":"Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation","created":"2022-09-28","cited_by_count":0,"area":null},{"id":"2401.15439","title":"Pre-training and Diagnosing Knowledge Base Completion Models","created":"2024-01-27","cited_by_count":0,"area":null},{"id":"2505.07833","title":"Harmonia: End-to-End RAG Serving Optimization","created":"2025-05-01","cited_by_count":0,"area":"rag"}],"next_cursor":null}