{"list":"other","total":54,"rows":[{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1802.03426","title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","created":"2018-02-09","cited_by_count":2898},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2004.14974","title":"Fact or Fiction: Verifying Scientific Claims","created":"2020-04-30","cited_by_count":554},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"2402.05672","title":"Multilingual E5 Text Embeddings: A Technical Report","created":"2024-02-08","cited_by_count":372},{"id":"2210.02410","title":"The Vendi Score: A Diversity Evaluation Metric for Machine Learning","created":"2022-10-05","cited_by_count":311},{"id":"1803.06992","title":"Estimating the intrinsic dimension of datasets by a minimal neighborhood information","created":"2018-03-19","cited_by_count":250},{"id":"2104.06967","title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling","created":"2021-04-14","cited_by_count":238},{"id":"1906.02715","title":"Visualizing and Measuring the Geometry of BERT","created":"2019-06-06","cited_by_count":216},{"id":"2012.00614","title":"CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims","created":"2020-12-01","cited_by_count":196},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143},{"id":"2211.14876","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","created":"2022-11-27","cited_by_count":136},{"id":"1908.02518","title":"Ripser: efficient computation of Vietoris-Rips persistence barcodes","created":"2019-08-07","cited_by_count":117},{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104},{"id":"2503.07891","title":"Gemini Embedding: Generalizable Embeddings from Gemini","created":"2025-03-10","cited_by_count":94},{"id":"2210.16156","title":"Reliability of CKA as a Similarity Measure in Deep Learning","created":"2022-10-28","cited_by_count":87},{"id":"2109.02596","title":"Scikit-dimension: a Python package for intrinsic dimension estimation","created":"2021-09-06","cited_by_count":68},{"id":"2201.00058","title":"Representation Topology Divergence: A Method for Comparing Neural Network Representations","created":"2021-12-31","cited_by_count":66},{"id":"2405.05374","title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models","created":"2024-05-08","cited_by_count":61},{"id":"2405.15471","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","created":"2024-05-24","cited_by_count":56},{"id":"2108.07344","title":"IsoScore: Measuring the Uniformity of Embedding Space Utilization","created":"2021-08-16","cited_by_count":53},{"id":"2404.07221","title":"Improving Retrieval for RAG based Question Answering Models on Financial Documents","created":"2024-03-23","cited_by_count":49},{"id":"2012.14210","title":"The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes","created":"2020-12-28","cited_by_count":48},{"id":"2311.05928","title":"The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models","created":"2023-11-10","cited_by_count":39},{"id":"1901.09785","title":"Evaluating Word Embedding Models: Methods and Experimental Results","created":"2019-01-28","cited_by_count":37},{"id":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32},{"id":"2403.15112","title":"Text Clustering with Large Language Model Embeddings","created":"2024-03-22","cited_by_count":27},{"id":"2005.04474","title":"TREC-COVID: Constructing a Pandemic Information Retrieval Test Collection","created":"2020-05-09","cited_by_count":23},{"id":"2411.05561","title":"Objective drives the consistency of representational similarity across datasets","created":"2024-11-08","cited_by_count":18},{"id":"2311.16054","title":"Metric Space Magnitude for Evaluating the Diversity of Latent Representations","created":"2023-11-27","cited_by_count":17},{"id":"2501.10573","title":"The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models","created":"2025-01-17","cited_by_count":17},{"id":"2410.01444","title":"Geometric Signatures of Compositionality Across a Language Model's Lifetime","created":"2024-10-02","cited_by_count":16},{"id":"2407.08275","title":"Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems","created":"2024-07-11","cited_by_count":12},{"id":"2410.11042","title":"Persistent Topological Features in Large Language Models","created":"2024-10-14","cited_by_count":12},{"id":"2406.07640","title":"When is an Embedding Model More Promising than Another?","created":"2024-06-11","cited_by_count":7},{"id":"2503.02142","title":"Measuring Intrinsic Dimension of Token Embeddings","created":"2025-03-04","cited_by_count":5},{"id":"2404.00500","title":"The Shape of Word Embeddings: Quantifying Non-Isometry With Topological Data Analysis","created":"2024-03-30","cited_by_count":4},{"id":"2405.17813","title":"The Impacts of Data, Ordering, and Intrinsic Dimensionality on Recall in Hierarchical Navigable Small Worlds","created":"2024-05-28","cited_by_count":4},{"id":"2506.00382","title":"Spectral Insights into Data-Oblivious Critical Layers in Large Language Models","created":"2025-05-31","cited_by_count":4},{"id":"1907.07387","title":"The Role of Local Intrinsic Dimensionality in Benchmarking Nearest Neighbor Search","created":"2019-07-17","cited_by_count":2},{"id":"2510.22953","title":"Manifold Approximation leads to Robust Kernel Alignment","created":"2025-10-27","cited_by_count":2}],"next_cursor":null}