{"list":"other","total":59,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2010.03240","title":"Bias and Debias in Recommender System: A Survey and Future Directions","created":"2020-10-07","cited_by_count":240},{"id":"1705.00652","title":"Efficient Natural Language Response Suggestion for Smart Reply","created":"2017-05-01","cited_by_count":229},{"id":"2110.07367","title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","created":"2021-10-14","cited_by_count":176},{"id":"1608.04468","title":"Unbiased Learning-to-Rank with Biased Feedback","created":"2016-08-16","cited_by_count":157},{"id":"2010.02666","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","created":"2020-10-06","cited_by_count":145},{"id":"2010.08240","title":"Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks","created":"2020-10-16","cited_by_count":138},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134},{"id":"2309.10621","title":"Large language models can accurately predict searcher preferences","created":"2023-09-19","cited_by_count":131},{"id":"1704.06879","title":"Deep Keyphrase Generation","created":"2017-04-23","cited_by_count":102},{"id":"2403.02839","title":"An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4","created":"2024-03-05","cited_by_count":94},{"id":"1810.05241","title":"One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases","created":"2018-10-11","cited_by_count":52},{"id":"2102.07831","title":"NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting","created":"2021-02-15","cited_by_count":41},{"id":"2205.09153","title":"ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval","created":"2022-05-18","cited_by_count":41},{"id":"2402.16829","title":"GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning","created":"2024-02-26","cited_by_count":40},{"id":"2111.06685","title":"DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents","created":"2021-11-12","cited_by_count":37},{"id":"1808.08575","title":"Title-Guided Encoding for Keyphrase Generation","created":"2018-08-26","cited_by_count":36},{"id":"2408.04303","title":"Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP","created":"2024-08-08","cited_by_count":36},{"id":"2207.04452","title":"NGAME: Negative Mining-aware Mini-batching for Extreme Classification","created":"2022-07-10","cited_by_count":32},{"id":"2010.10999","title":"Is Retriever Merely an Approximator of Reader?","created":"2020-10-21","cited_by_count":30},{"id":"1904.03454","title":"An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction","created":"2019-04-06","cited_by_count":28},{"id":"2406.01285","title":"Large Language Models as Recommender Systems: A Study of Popularity Bias","created":"2024-06-03","cited_by_count":26},{"id":"2409.15133","title":"Don't Use LLMs to Make Relevance Judgments","created":"2024-09-23","cited_by_count":26},{"id":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","cited_by_count":21},{"id":"2202.12690","title":"On Modality Bias Recognition and Reduction","created":"2022-02-25","cited_by_count":20},{"id":"2502.18460","title":"DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers","created":"2025-02-25","cited_by_count":19},{"id":"2205.05812","title":"Open Vocabulary Extreme Classification Using Generative Models","created":"2022-05-12","cited_by_count":13},{"id":"2211.06862","title":"WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation","created":"2022-11-13","cited_by_count":13},{"id":"2306.03527","title":"Rec4Ad: A Free Lunch to Mitigate Sample Selection Bias for Ads CTR Prediction in Taobao","created":"2023-06-06","cited_by_count":11},{"id":"2405.06932","title":"Piccolo2: General Text Embedding with Multi-task Hybrid Loss Training","created":"2024-05-11","cited_by_count":10},{"id":"2406.17262","title":"D2LLM: Decomposed and Distilled Large Language Models for Semantic Search","created":"2024-06-25","cited_by_count":9},{"id":"2410.17152","title":"Improving Pinterest Search Relevance Using Large Language Models","created":"2024-10-22","cited_by_count":8},{"id":"2304.09560","title":"An Offline Metric for the Debiasedness of Click Models","created":"2023-04-19","cited_by_count":6},{"id":"2407.20462","title":"Graphite: A Graph-based Extreme Multi-Label Short Text Classifier for Keyphrase Recommendation","created":"2024-07-29","cited_by_count":6},{"id":"2101.11349","title":"Triangular Bidword Generation for Sponsored Search Auction","created":"2021-01-27","cited_by_count":5},{"id":"2408.08981","title":"From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning","created":"2024-08-16","cited_by_count":5},{"id":"2505.04209","title":"To Judge or not to Judge: Using LLM Judgements for Advertiser Keyphrase Relevance at eBay","created":"2025-05-07","cited_by_count":4},{"id":"2409.03140","title":"GraphEx: A Graph-based Extraction Method for Advertiser Keyphrase Recommendation","created":"2024-09-05","cited_by_count":3},{"id":"2502.00131","title":"Middleman Bias in Advertising: Aligning Relevance of Keyphrase Recommendations with Search","created":"2025-01-31","cited_by_count":3},{"id":"2108.10197","title":"Deploying a BERT-based Query-Title Relevance Classifier in a Production System: a View from the Trenches","created":"2021-08-23","cited_by_count":2},{"id":"2504.07110","title":"DashCLIP: Leveraging multimodal models for generating semantic embeddings for DoorDash","created":"2025-03-18","cited_by_count":2},{"id":"2505.19274","title":"Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data","created":"2025-05-25","cited_by_count":2},{"id":"2505.19164","title":"BroadGen: A Framework for Generating Effective and Efficient Advertiser Broad Match Keyphrase Recommendations","created":"2025-05-25","cited_by_count":1}],"next_cursor":null}