{"list":"other","total":58,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2010.08191","title":"RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-10-16","cited_by_count":413},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"2003.07820","title":"Overview of the TREC 2019 deep learning track","created":"2020-03-17","cited_by_count":286},{"id":"2310.08319","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","created":"2023-10-12","cited_by_count":272},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"id":"1602.05352","title":"Recommendations as Treatments: Debiasing Learning and Evaluation","created":"2016-02-17","cited_by_count":248},{"id":"2010.03240","title":"Bias and Debias in Recommender System: A Survey and Future Directions","created":"2020-10-07","cited_by_count":240},{"id":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235},{"id":"1811.04820","title":"Learning from positive and unlabeled data: a survey","created":"2018-11-12","cited_by_count":219},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161},{"id":"1608.04468","title":"Unbiased Learning-to-Rank with Biased Feedback","created":"2016-08-16","cited_by_count":157},{"id":"2309.10621","title":"Large language models can accurately predict searcher preferences","created":"2023-09-19","cited_by_count":131},{"id":"1811.01727","title":"AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification","created":"2018-11-01","cited_by_count":102},{"id":"1506.08839","title":"Inferring Networks of Substitutable and Complementary Products","created":"2015-06-29","cited_by_count":92},{"id":"1909.03601","title":"Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback","created":"2019-09-09","cited_by_count":79},{"id":"2403.03187","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","created":"2024-03-05","cited_by_count":73},{"id":"1609.02521","title":"DiSMEC - Distributed Sparse Machines for Extreme Multi-label Classification","created":"2016-09-08","cited_by_count":71},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67},{"id":"1904.08249","title":"Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification","created":"2019-04-17","cited_by_count":61},{"id":"2101.03305","title":"LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification","created":"2021-01-09","cited_by_count":61},{"id":"2305.14288","title":"LLM-powered Data Augmentation for Enhanced Cross-lingual Performance","created":"2023-05-23","cited_by_count":51},{"id":"2206.10658","title":"Questions Are All You Need to Train a Dense Passage Retriever","created":"2022-06-21","cited_by_count":47},{"id":"1910.09337","title":"Large-scale Causal Approaches to Debiasing Post-click Conversion Rate Estimation with Multi-task Learning","created":"2019-10-16","cited_by_count":39},{"id":"2108.00261","title":"ECLARE: Extreme Classification with Label Graph Correlations","created":"2021-07-31","cited_by_count":38},{"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":"1910.13830","title":"Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products","created":"2019-10-28","cited_by_count":36},{"id":"2404.14361","title":"Better Synthetic Data by Retrieving and Transforming Existing Datasets","created":"2024-04-22","cited_by_count":36},{"id":"2006.05324","title":"ORCAS: 18 Million Clicked Query-Document Pairs for Analyzing Search","created":"2020-06-09","cited_by_count":34},{"id":"2108.00368","title":"DECAF: Deep Extreme Classification with Label Features","created":"2021-08-01","cited_by_count":33},{"id":"2207.04452","title":"NGAME: Negative Mining-aware Mini-batching for Extreme Classification","created":"2022-07-10","cited_by_count":32},{"id":"1810.07076","title":"Stochastic Negative Mining for Learning with Large Output Spaces","created":"2018-10-16","cited_by_count":29},{"id":"2209.09900","title":"LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging","created":"2022-09-20","cited_by_count":29},{"id":"2310.20111","title":"Making Large Language Models Better Data Creators","created":"2023-10-31","cited_by_count":28},{"id":"2007.02439","title":"Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classification","created":"2020-07-05","cited_by_count":25},{"id":"2205.04701","title":"StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random","created":"2022-05-10","cited_by_count":24},{"id":"2405.07767","title":"Synthetic Test Collections for Retrieval Evaluation","created":"2024-05-13","cited_by_count":19},{"id":"2402.14273","title":"Can Language Models Act as Knowledge Bases at Scale?","created":"2024-02-22","cited_by_count":17},{"id":"2207.13186","title":"On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification","created":"2022-07-26","cited_by_count":15},{"id":"2210.08410","title":"ELIAS: End-to-End Learning to Index and Search in Large Output Spaces","created":"2022-10-16","cited_by_count":14},{"id":"1802.06565","title":"A Study of Position Bias in Digital Library Recommender Systems","created":"2018-02-19","cited_by_count":13},{"id":"2105.05736","title":"Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces","created":"2021-05-12","cited_by_count":9},{"id":"2110.10803","title":"Propensity-scored Probabilistic Label Trees","created":"2021-10-20","cited_by_count":8},{"id":"2310.10636","title":"Dual-Encoders for Extreme Multi-Label Classification","created":"2023-10-16","cited_by_count":7},{"id":"2403.00817","title":"Doubly Calibrated Estimator for Recommendation on Data Missing Not At Random","created":"2024-02-26","cited_by_count":7},{"id":"2209.05861","title":"Unified Generative & Dense Retrieval for Query Rewriting in Sponsored Search","created":"2022-09-13","cited_by_count":6},{"id":"2301.11309","title":"SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme Classification","created":"2023-01-26","cited_by_count":6},{"id":"1808.08755","title":"Learning from Positive and Unlabeled Data under the Selected At Random Assumption","created":"2018-08-27","cited_by_count":5},{"id":"2305.12768","title":"uCTRL: Unbiased Contrastive Representation Learning via Alignment and Uniformity for Collaborative Filtering","created":"2023-05-22","cited_by_count":5},{"id":"2402.18434","title":"Graph Regularized Encoder Training for Extreme Classification","created":"2024-02-28","cited_by_count":1}],"next_cursor":null}