{"list":"other","total":70,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"1803.11175","title":"Universal Sentence Encoder","created":"2018-03-29","cited_by_count":489},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"2308.11462","title":"LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models","created":"2023-08-20","cited_by_count":336},{"id":"1307.5336","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","created":"2013-07-19","cited_by_count":310},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"2407.19669","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","created":"2024-07-29","cited_by_count":236},{"id":"1705.00652","title":"Efficient Natural Language Response Suggestion for Smart Reply","created":"2017-05-01","cited_by_count":229},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180},{"id":"1904.09658","title":"Probabilistic Face Embeddings","created":"2019-04-21","cited_by_count":173},{"id":"1906.03741","title":"BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization","created":"2019-06-10","cited_by_count":156},{"id":"2109.04404","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","created":"2021-09-09","cited_by_count":156},{"id":"2305.16307","title":"IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages","created":"2023-05-25","cited_by_count":152},{"id":"2309.07445","title":"SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects","created":"2023-09-14","cited_by_count":152},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"1412.6623","title":"Word Representations via Gaussian Embedding","created":"2014-12-20","cited_by_count":96},{"id":"1904.07094","title":"CEDR: Contextualized Embeddings for Document Ranking","created":"2019-04-15","cited_by_count":77},{"id":"2211.06291","title":"Do Bayesian Neural Networks Need To Be Fully Stochastic?","created":"2022-11-11","cited_by_count":63},{"id":"2110.00806","title":"Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark","created":"2021-10-02","cited_by_count":60},{"id":"2304.03679","title":"T2Ranking: A large-scale Chinese Benchmark for Passage Ranking","created":"2023-04-07","cited_by_count":60},{"id":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60},{"id":"2404.16816","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","created":"2024-04-25","cited_by_count":56},{"id":"1810.00319","title":"Modeling Uncertainty with Hedged Instance Embedding","created":"2018-09-30","cited_by_count":52},{"id":"2011.02686","title":"Investigating Societal Biases in a Poetry Composition System","created":"2020-11-05","cited_by_count":48},{"id":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43},{"id":"2210.05335","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","created":"2022-10-11","cited_by_count":41},{"id":"2305.18171","title":"Improved Probabilistic Image-Text Representations","created":"2023-05-29","cited_by_count":40},{"id":"2104.07081","title":"TWEAC: Transformer with Extendable QA Agent Classifiers","created":"2021-04-14","cited_by_count":37},{"id":"2003.01227","title":"Fast Predictive Uncertainty for Classification with Bayesian Deep Networks","created":"2020-03-02","cited_by_count":31},{"id":"2304.09972","title":"MasakhaNEWS: News Topic Classification for African languages","created":"2023-04-19","cited_by_count":31},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29},{"id":"2111.03577","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","created":"2021-11-05","cited_by_count":25},{"id":"2209.09824","title":"Twitter Topic Classification","created":"2022-09-20","cited_by_count":22},{"id":"2402.08638","title":"SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages","created":"2024-02-13","cited_by_count":16},{"id":"2410.18857","title":"Probabilistic Language-Image Pre-Training","created":"2024-10-24","cited_by_count":16},{"id":"2401.13875","title":"Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?","created":"2024-01-25","cited_by_count":15},{"id":"2412.06014","title":"Post-hoc Probabilistic Vision-Language Models","created":"2024-12-08","cited_by_count":13},{"id":"2203.00537","title":"DynamicRetriever: A Pre-training Model-based IR System with Neither Sparse nor Dense Index","created":"2022-03-01","cited_by_count":12},{"id":"1603.06571","title":"Bayesian Neural Word Embedding","created":"2016-03-21","cited_by_count":11},{"id":"2505.05163","title":"Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models","created":"2025-05-08","cited_by_count":9},{"id":"2304.14869","title":"On the 1-Wasserstein Distance between Location-Scale Distributions and the Effect of Differential Privacy","created":"2023-04-28","cited_by_count":7},{"id":"2302.07738","title":"Alloprof: a new French question-answer education dataset and its use in an information retrieval case study","created":"2023-02-10","cited_by_count":6},{"id":"2312.10464","title":"Identity Curvature Laplace Approximation for Improved Out-of-Distribution Detection","created":"2023-12-16","cited_by_count":4},{"id":"2306.14939","title":"The Art of Embedding Fusion: Optimizing Hate Speech Detection","created":"2023-06-26","cited_by_count":3},{"id":"1511.06246","title":"Gaussian Mixture Embeddings for Multiple Word Prototypes","created":"2015-11-19","cited_by_count":1},{"id":"2104.06719","title":"Sentence Embeddings by Ensemble Distillation","created":"2021-04-14","cited_by_count":1},{"id":"2306.02247","title":"Sen2Pro: A Probabilistic Perspective to Sentence Embedding from Pre-trained Language Model","created":"2023-06-04","cited_by_count":1},{"id":"2311.08235","title":"Inference of Probabilistic Programs with Moment-Matching Gaussian Mixtures","created":"2023-11-14","cited_by_count":1},{"id":"2501.15876","title":"Optimizing Sentence Embedding with Pseudo-Labeling and Model Ensembles: A Hierarchical Framework for Enhanced NLP Tasks","created":"2025-01-27","cited_by_count":1}],"next_cursor":null}