{"total":784,"rows":[{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173,"area":null},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561,"area":null},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298,"area":null},{"id":"2307.03393","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","created":"2023-07-07","cited_by_count":274,"area":null},{"id":"2306.06031","title":"FinGPT: Open-Source Financial Large Language Models","created":"2023-06-09","cited_by_count":253,"area":null},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2202.06417","title":"A Contrastive Framework for Neural Text Generation","created":"2022-02-13","cited_by_count":225,"area":null},{"id":"2205.05124","title":"Extracting Latent Steering Vectors from Pretrained Language Models","created":"2022-05-10","cited_by_count":225,"area":"mechinterp"},{"id":"2202.08904","title":"SGPT: GPT Sentence Embeddings for Semantic Search","created":"2022-02-17","cited_by_count":204,"area":null},{"id":"2103.15316","title":"Whitening Sentence Representations for Better Semantics and Faster Retrieval","created":"2021-03-29","cited_by_count":202,"area":null},{"id":"2311.13743","title":"FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design","created":"2023-11-23","cited_by_count":164,"area":"agents"},{"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,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2102.09550","title":"Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer","created":"2021-02-18","cited_by_count":134,"area":null},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"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":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112,"area":null},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108,"area":null},{"id":"2403.02901","title":"A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods","created":"2024-03-05","cited_by_count":102,"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":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2307.16645","title":"Scaling Sentence Embeddings with Large Language Models","created":"2023-07-31","cited_by_count":85,"area":null},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82,"area":null},{"id":"2201.04337","title":"PromptBERT: Improving BERT Sentence Embeddings with Prompts","created":"2022-01-12","cited_by_count":75,"area":null},{"id":"2406.08619","title":"Self-Supervised Speech Representations are More Phonetic than Semantic","created":"2024-06-12","cited_by_count":71,"area":null},{"id":"2112.02690","title":"Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification","created":"2021-12-05","cited_by_count":67,"area":null},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65,"area":null},{"id":"2101.00403","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","created":"2021-01-02","cited_by_count":63,"area":null},{"id":"2401.12143","title":"Anisotropy Is Inherent to Self-Attention in Transformers","created":"2024-01-22","cited_by_count":63,"area":null},{"id":"2502.12119","title":"PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection","created":"2025-02-17","cited_by_count":61,"area":"mllm"},{"id":"2602.11451","title":"LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation","created":"2026-02-11","cited_by_count":61,"area":"lr"},{"id":"2210.14140","title":"Contrastive Search Is What You Need For Neural Text Generation","created":"2022-10-25","cited_by_count":59,"area":null},{"id":"2502.01951","title":"On the Emergence of Position Bias in Transformers","created":"2025-02-04","cited_by_count":59,"area":null},{"id":"2205.00656","title":"Debiased Contrastive Learning of Unsupervised Sentence Representations","created":"2022-05-02","cited_by_count":56,"area":null},{"id":"2205.07237","title":"Discovering Latent Concepts Learned in BERT","created":"2022-05-15","cited_by_count":56,"area":null},{"id":"2205.11380","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","created":"2022-05-23","cited_by_count":55,"area":null},{"id":"2108.07344","title":"IsoScore: Measuring the Uniformity of Embedding Space Utilization","created":"2021-08-16","cited_by_count":53,"area":null},{"id":"2302.06461","title":"A Study on ReLU and Softmax in Transformer","created":"2023-02-13","cited_by_count":53,"area":null},{"id":"2402.10962","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","created":"2024-02-13","cited_by_count":53,"area":null},{"id":"2109.07152","title":"Incorporating Residual and Normalization Layers into Analysis of Masked Language Models","created":"2021-09-15","cited_by_count":51,"area":null},{"id":"2202.06840","title":"What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code","created":"2022-02-14","cited_by_count":50,"area":null},{"id":"2505.13898","title":"Do Language Models Use Their Depth Efficiently?","created":"2025-05-20","cited_by_count":50,"area":null},{"id":"2205.05092","title":"Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words","created":"2022-05-10","cited_by_count":49,"area":null},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48,"area":"mllm"},{"id":"2405.18781","title":"On the Role of Attention Masks and LayerNorm in Transformers","created":"2024-05-29","cited_by_count":48,"area":null},{"id":"2403.01509","title":"Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics","created":"2024-03-03","cited_by_count":44,"area":null},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"area":null},{"id":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40,"area":null},{"id":"2212.09412","title":"Empowering Diffusion Models on the Embedding Space for Text Generation","created":"2022-12-19","cited_by_count":40,"area":"diffusion"},{"id":"2104.14694","title":"Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses","created":"2021-04-29","cited_by_count":39,"area":null},{"id":"2110.00672","title":"Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models","created":"2021-10-01","cited_by_count":39,"area":null},{"id":"2303.06562","title":"ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond","created":"2023-03-12","cited_by_count":39,"area":null},{"id":"2311.05928","title":"The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models","created":"2023-11-10","cited_by_count":39,"area":null},{"id":"2501.03747","title":"Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series","created":"2025-01-07","cited_by_count":39,"area":null},{"id":"2305.16292","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","created":"2023-05-25","cited_by_count":38,"area":null},{"id":"2405.13055","title":"Large Language Models for Medicine: A Survey","created":"2024-05-20","cited_by_count":38,"area":null},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38,"area":null},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38,"area":null},{"id":"2111.02194","title":"Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training","created":"2021-11-03","cited_by_count":37,"area":null},{"id":"2305.14976","title":"GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP","created":"2023-05-24","cited_by_count":37,"area":null},{"id":"2407.21065","title":"LawLLM: Law Large Language Model for the US Legal System","created":"2024-07-27","cited_by_count":37,"area":null},{"id":"2103.07259","title":"Explaining and Improving BERT Performance on Lexical Semantic Change Detection","created":"2021-03-12","cited_by_count":34,"area":null},{"id":"2106.05426","title":"Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses","created":"2021-06-09","cited_by_count":34,"area":null},{"id":"2303.08014","title":"Do large language models resemble humans in language use?","created":"2023-03-10","cited_by_count":34,"area":null},{"id":"2404.06228","title":"Understanding Cross-Lingual Alignment -- A Survey","created":"2024-04-09","cited_by_count":34,"area":null},{"id":"2111.04198","title":"TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning","created":"2021-11-07","cited_by_count":32,"area":null},{"id":"2311.05296","title":"BeLLM: Backward Dependency Enhanced Large Language Model for Sentence Embeddings","created":"2023-11-09","cited_by_count":32,"area":null},{"id":"2401.17671","title":"Contextual Feature Extraction Hierarchies Converge in Large Language Models and the Brain","created":"2024-01-31","cited_by_count":32,"area":null},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2401.08495","title":"Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans","created":"2024-01-16","cited_by_count":31,"area":null},{"id":"2407.02235","title":"Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report Generation","created":"2024-07-02","cited_by_count":31,"area":"mllm"},{"id":"2105.14652","title":"Attention Flows are Shapley Value Explanations","created":"2021-05-31","cited_by_count":30,"area":null},{"id":"2203.06875","title":"Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning","created":"2022-03-14","cited_by_count":30,"area":null},{"id":"2305.19249","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","created":"2023-05-30","cited_by_count":29,"area":null},{"id":"2502.01615","title":"Large Language Models Are Human-Like Internally","created":"2025-02-03","cited_by_count":29,"area":"mechinterp"},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2106.01183","title":"A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space","created":"2021-06-02","cited_by_count":27,"area":null},{"id":"2109.03127","title":"Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings","created":"2021-09-07","cited_by_count":27,"area":null},{"id":"2104.12465","title":"GPT2MVS: Generative Pre-trained Transformer-2 for Multi-modal Video Summarization","created":"2021-04-26","cited_by_count":26,"area":null},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2110.04504","title":"An Isotropy Analysis in the Multilingual BERT Embedding Space","created":"2021-10-09","cited_by_count":25,"area":null},{"id":"2202.12246","title":"Neural reality of argument structure constructions","created":"2022-02-24","cited_by_count":25,"area":null},{"id":"2402.04852","title":"Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning","created":"2024-02-07","cited_by_count":25,"area":null},{"id":"2408.04604","title":"Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning","created":"2024-08-08","cited_by_count":25,"area":null},{"id":"2410.05873","title":"MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2105.01736","title":"Retrieving Complex Tables with Multi-Granular Graph Representation Learning","created":"2021-05-04","cited_by_count":24,"area":null},{"id":"2408.15417","title":"Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations","created":"2024-08-27","cited_by_count":24,"area":null},{"id":"2104.05274","title":"Learning to Remove: Towards Isotropic Pre-trained BERT Embedding","created":"2021-04-12","cited_by_count":23,"area":null},{"id":"2106.02596","title":"Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model","created":"2021-06-04","cited_by_count":23,"area":null},{"id":"2109.04740","title":"How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropy","created":"2021-09-10","cited_by_count":23,"area":null},{"id":"2305.16726","title":"RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank","created":"2023-05-26","cited_by_count":23,"area":null},{"id":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","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":"2210.07269","title":"SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models","created":"2022-10-13","cited_by_count":22,"area":"lr"},{"id":"2304.04591","title":"For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal","created":"2023-04-10","cited_by_count":22,"area":"offlinerl"}],"next_cursor":"100"}