{"total":120,"rows":[{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252,"area":null},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801,"area":null},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"area":null},{"id":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204,"area":null},{"id":"2104.08253","title":"Condenser: a Pre-training Architecture for Dense Retrieval","created":"2021-04-16","cited_by_count":162,"area":null},{"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":"2112.07577","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","created":"2021-12-14","cited_by_count":119,"area":null},{"id":"2302.07452","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","created":"2023-02-15","cited_by_count":118,"area":null},{"id":"2104.08027","title":"Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders","created":"2021-04-16","cited_by_count":88,"area":null},{"id":"2110.01852","title":"Data Augmentation Approaches in Natural Language Processing: A Survey","created":"2021-10-05","cited_by_count":82,"area":null},{"id":"2104.01767","title":"WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach","created":"2021-04-05","cited_by_count":69,"area":null},{"id":"2303.00807","title":"UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers","created":"2023-03-01","cited_by_count":37,"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":"2206.07023","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2306.15766","title":"Large Language Models as Annotators: Enhancing Generalization of NLP Models at Minimal Cost","created":"2023-06-27","cited_by_count":33,"area":null},{"id":"2109.05424","title":"Pairwise Supervised Contrastive Learning of Sentence Representations","created":"2021-09-12","cited_by_count":31,"area":null},{"id":"2106.06719","title":"Improving Unsupervised Dialogue Topic Segmentation with Utterance-Pair Coherence Scoring","created":"2021-06-12","cited_by_count":29,"area":null},{"id":"2103.11933","title":"PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERT","created":"2021-03-22","cited_by_count":24,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2505.15045","title":"Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective","created":"2025-05-21","cited_by_count":23,"area":null},{"id":"2112.11031","title":"On Cross-Lingual Retrieval with Multilingual Text Encoders","created":"2021-12-21","cited_by_count":22,"area":null},{"id":"2204.12755","title":"A Thorough Examination on Zero-shot Dense Retrieval","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2109.13059","title":"Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2105.12936","title":"Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence","created":"2021-05-27","cited_by_count":19,"area":null},{"id":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"area":null},{"id":"2210.16798","title":"Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework","created":"2022-10-30","cited_by_count":19,"area":null},{"id":"2412.15540","title":"MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering","created":"2024-12-20","cited_by_count":17,"area":null},{"id":"2211.05165","title":"Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database","created":"2022-11-09","cited_by_count":16,"area":null},{"id":"2209.04333","title":"Ranking-Enhanced Unsupervised Sentence Representation Learning","created":"2022-09-09","cited_by_count":15,"area":null},{"id":"2305.17804","title":"Targeted Data Generation: Finding and Fixing Model Weaknesses","created":"2023-05-28","cited_by_count":15,"area":null},{"id":"2208.12306","title":"Multimedia Generative Script Learning for Task Planning","created":"2022-08-25","cited_by_count":12,"area":null},{"id":"2301.04283","title":"MGeo: Multi-Modal Geographic Pre-Training Method","created":"2023-01-11","cited_by_count":12,"area":null},{"id":"2305.12641","title":"A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond","created":"2023-05-22","cited_by_count":12,"area":null},{"id":"2405.11579","title":"Exploring the Capabilities of Prompted Large Language Models in Educational and Assessment Applications","created":"2024-05-19","cited_by_count":12,"area":null},{"id":"2504.08125","title":"Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects","created":"2025-04-10","cited_by_count":11,"area":null},{"id":"2210.12579","title":"Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization","created":"2022-10-23","cited_by_count":10,"area":null},{"id":"2312.09634","title":"Vectorizing string entries for data processing on tables: when are larger language models better?","created":"2023-12-15","cited_by_count":10,"area":null},{"id":"2210.04447","title":"CrowdChecked: Detecting Previously Fact-Checked Claims in Social Media","created":"2022-10-10","cited_by_count":9,"area":null},{"id":"2204.13021","title":"NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-04-27","cited_by_count":8,"area":null},{"id":"2303.08032","title":"Verifying the Robustness of Automatic Credibility Assessment","created":"2023-03-14","cited_by_count":8,"area":null},{"id":"2205.12502","title":"The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training","created":"2022-05-25","cited_by_count":7,"area":null},{"id":"2210.16953","title":"Improving Bilingual Lexicon Induction with Cross-Encoder Reranking","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2305.18638","title":"Short Answer Grading Using One-shot Prompting and Text Similarity Scoring Model","created":"2023-05-29","cited_by_count":7,"area":null},{"id":"2312.14106","title":"Learning Human-like Representations to Enable Learning Human Values","created":"2023-12-21","cited_by_count":7,"area":null},{"id":"2410.08393","title":"The Effects of Hallucinations in Synthetic Training Data for Relation Extraction","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2112.08772","title":"Sharpness-Aware Minimization with Dynamic Reweighting","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2203.13491","title":"Striking a Balance: Alleviating Inconsistency in Pre-trained Models for Symmetric Classification Tasks","created":"2022-03-25","cited_by_count":6,"area":null},{"id":"2411.17719","title":"SlideSpawn: An Automatic Slides Generation System for Research Publications","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2602.12192","title":"Query-focused and Memory-aware Reranker for Long Context Processing","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2208.00231","title":"Masked Autoencoders As The Unified Learners For Pre-Trained Sentence Representation","created":"2022-07-30","cited_by_count":5,"area":null},{"id":"2210.13749","title":"AugCSE: Contrastive Sentence Embedding with Diverse Augmentations","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2301.02736","title":"Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition","created":"2023-01-06","cited_by_count":5,"area":null},{"id":"2406.05326","title":"Advancing Semantic Textual Similarity Modeling: A Regression Framework with Translated ReLU and Smooth K2 Loss","created":"2024-06-08","cited_by_count":5,"area":null},{"id":"2310.08122","title":"Core-sets for Fair and Diverse Data Summarization","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2312.02803","title":"Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2402.07788","title":"Multi-Intent Attribute-Aware Text Matching in Searching","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2505.24613","title":"When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2508.19758","title":"Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrieval","created":"2025-08-27","cited_by_count":4,"area":null},{"id":"2209.14494","title":"Multi-stage Information Retrieval for Vietnamese Legal Texts","created":"2022-09-29","cited_by_count":3,"area":null},{"id":"2304.04918","title":"Explicit and Implicit Semantic Ranking Framework","created":"2023-04-11","cited_by_count":3,"area":null},{"id":"2403.16630","title":"A comparative analysis of embedding models for patent similarity","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2504.01127","title":"Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Bench","created":"2025-04-01","cited_by_count":3,"area":null},{"id":"2103.10673","title":"Cost-effective Deployment of BERT Models in Serverless Environment","created":"2021-03-19","cited_by_count":2,"area":null},{"id":"2110.15725","title":"Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring Tasks","created":"2021-10-10","cited_by_count":2,"area":null},{"id":"2302.01806","title":"Mitigating Data Scarcity for Large Language Models","created":"2023-02-03","cited_by_count":2,"area":null},{"id":"2302.11412","title":"Data Augmentation for Neural NLP","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2308.10354","title":"Imaginations of WALL-E : Reconstructing Experiences with an Imagination-Inspired Module for Advanced AI Systems","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2310.04965","title":"MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2407.08248","title":"Toward accessible comics for blind and low vision readers","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2410.23510","title":"Tiny Transformers Excel at Sentence Compression","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2502.14275","title":"Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2507.09797","title":"A Scalable and Efficient Signal Integration System for Job Matching","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2508.03628","title":"LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2510.08601","title":"Mnemosyne: An Unsupervised, Human-Inspired Long-Term Memory Architecture for Edge-Based LLMs","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2604.12342","title":"CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2104.08340","title":"An Analysis of a BERT Deep Learning Strategy on a Technology Assisted Review Task","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2201.00693","title":"Multimodal Entity Tagging with Multimodal Knowledge Base","created":"2021-12-21","cited_by_count":1,"area":null},{"id":"2205.15812","title":"GateNLP-UShef at SemEval-2022 Task 8: Entity-Enriched Siamese Transformer for Multilingual News Article Similarity","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2206.08263","title":"'John ate 5 apples' != 'John ate some apples': Self-Supervised Paraphrase Quality Detection for Algebraic Word Problems","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2206.12664","title":"Evaluation of Semantic Answer Similarity Metrics","created":"2022-06-25","cited_by_count":1,"area":null},{"id":"2208.09243","title":"Pseudo-Labels Are All You Need","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2210.05302","title":"Towards Structure-aware Paraphrase Identification with Phrase Alignment Using Sentence Encoders","created":"2022-10-11","cited_by_count":1,"area":null},{"id":"2210.10636","title":"Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems","created":"2022-10-07","cited_by_count":1,"area":null},{"id":"2309.06131","title":"Annotating Data for Fine-Tuning a Neural Ranker? Current Active Learning Strategies are not Better than Random Selection","created":"2023-09-12","cited_by_count":1,"area":null},{"id":"2405.03651","title":"Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders","created":"2024-05-06","cited_by_count":1,"area":null},{"id":"2406.03673","title":"Linguistically Conditioned Semantic Textual Similarity","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2512.04351","title":"Distance Is All You Need: Radial Dispersion for Uncertainty Estimation in Large Language Models","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2106.02363","title":"Learning Slice-Aware Representations with Mixture of Attentions","created":"2021-06-04","cited_by_count":0,"area":null},{"id":"2204.10558","title":"Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues","created":"2022-04-22","cited_by_count":0,"area":null},{"id":"2304.01974","title":"Dialogue-Contextualized Re-ranking for Medical History-Taking","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2305.18977","title":"Cross Encoding as Augmentation: Towards Effective Educational Text Classification","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2307.00008","title":"Investigating Masking-based Data Generation in Language Models","created":"2023-06-16","cited_by_count":0,"area":null},{"id":"2307.14899","title":"Retrieval-based Text Selection for Addressing Class-Imbalanced Data in Classification","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2311.04139","title":"Modelling Sentiment Analysis: LLMs and data augmentation techniques","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2311.14076","title":"Searching for Snippets of Open-Domain Dialogue in Task-Oriented Dialogue Datasets","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2402.02932","title":"Domain Adaptation of Multilingual Semantic Search -- Literature Review","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2402.06766","title":"Evaluation Metrics for Text Data Augmentation in NLP","created":"2024-02-09","cited_by_count":0,"area":null},{"id":"2405.13008","title":"Control Token with Dense Passage Retrieval","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2406.13695","title":"Multilingual De-Duplication Strategies: Applying scalable similarity search with monolingual & multilingual embedding models","created":"2024-06-19","cited_by_count":0,"area":null}],"next_cursor":"100"}