{"total":139,"rows":[{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675,"area":null},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553,"area":null},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532,"area":null},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528,"area":null},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307,"area":"inference"},{"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":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150,"area":null},{"id":"2204.05832","title":"What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?","created":"2022-04-12","cited_by_count":150,"area":null},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132,"area":null},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128,"area":null},{"id":"2202.08005","title":"Should You Mask 15% in Masked Language Modeling?","created":"2022-02-16","cited_by_count":118,"area":null},{"id":"2104.03466","title":"Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT","created":"2021-04-08","cited_by_count":104,"area":null},{"id":"2401.04700","title":"Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue","created":"2024-01-09","cited_by_count":103,"area":null},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98,"area":null},{"id":"2205.10964","title":"The Geometry of Multilingual Language Model Representations","created":"2022-05-22","cited_by_count":95,"area":null},{"id":"2303.09435","title":"Jump to Conclusions: Short-Cutting Transformers With Linear Transformations","created":"2023-03-16","cited_by_count":90,"area":null},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88,"area":null},{"id":"2201.00058","title":"Representation Topology Divergence: A Method for Comparing Neural Network Representations","created":"2021-12-31","cited_by_count":66,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"area":null},{"id":"2406.13415","title":"Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators","created":"2024-06-19","cited_by_count":61,"area":null},{"id":"2310.11877","title":"The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models","created":"2023-10-18","cited_by_count":55,"area":null},{"id":"2409.01658","title":"From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning","created":"2024-09-03","cited_by_count":54,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2205.11631","title":"Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer","created":"2022-05-23","cited_by_count":45,"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":"2305.06212","title":"Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services","created":"2023-05-10","cited_by_count":43,"area":null},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"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":"2406.12094","title":"Who's asking? User personas and the mechanics of latent misalignment","created":"2024-06-17","cited_by_count":40,"area":"safety"},{"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":"2402.11455","title":"LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks","created":"2024-02-18","cited_by_count":39,"area":null},{"id":"2104.05882","title":"Discourse Probing of Pretrained Language Models","created":"2021-04-13","cited_by_count":38,"area":null},{"id":"2108.12463","title":"Automatic Text Evaluation through the Lens of Wasserstein Barycenters","created":"2021-08-27","cited_by_count":38,"area":null},{"id":"2105.14802","title":"On Compositional Generalization of Neural Machine Translation","created":"2021-05-31","cited_by_count":34,"area":null},{"id":"2310.19704","title":"A Survey on Knowledge Editing of Neural Networks","created":"2023-10-30","cited_by_count":34,"area":null},{"id":"2109.08406","title":"Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers","created":"2021-09-17","cited_by_count":30,"area":null},{"id":"2104.01477","title":"Exploring the Role of BERT Token Representations to Explain Sentence Probing Results","created":"2021-04-03","cited_by_count":29,"area":null},{"id":"2205.15301","title":"Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation","created":"2022-05-30","cited_by_count":28,"area":null},{"id":"2108.12197","title":"Translation Error Detection as Rationale Extraction","created":"2021-08-27","cited_by_count":22,"area":null},{"id":"2311.00522","title":"Text Rendering Strategies for Pixel Language Models","created":"2023-11-01","cited_by_count":22,"area":null},{"id":"2107.05431","title":"CoBERL: Contrastive BERT for Reinforcement Learning","created":"2021-07-12","cited_by_count":21,"area":null},{"id":"2206.03529","title":"How to Dissect a Muppet: The Structure of Transformer Embedding Spaces","created":"2022-06-07","cited_by_count":20,"area":null},{"id":"2105.12449","title":"LMMS Reloaded: Transformer-based Sense Embeddings for Disambiguation and Beyond","created":"2021-05-26","cited_by_count":17,"area":null},{"id":"2402.13137","title":"The Hidden Space of Transformer Language Adapters","created":"2024-02-20","cited_by_count":17,"area":null},{"id":"2109.05958","title":"Not All Models Localize Linguistic Knowledge in the Same Place: A Layer-wise Probing on BERToids' Representations","created":"2021-09-13","cited_by_count":16,"area":null},{"id":"2105.13471","title":"Inspecting the concept knowledge graph encoded by modern language models","created":"2021-05-27","cited_by_count":15,"area":null},{"id":"2203.10378","title":"On Robust Prefix-Tuning for Text Classification","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2404.11225","title":"In-Context Learning State Vector with Inner and Momentum Optimization","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2503.19693","title":"AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation","created":"2025-03-25","cited_by_count":15,"area":null},{"id":"2602.00462","title":"LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs","created":"2026-01-31","cited_by_count":15,"area":"mllm"},{"id":"2605.11011","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","created":"2026-05-10","cited_by_count":15,"area":"lr"},{"id":"2203.07511","title":"Contrastive Visual Semantic Pretraining Magnifies the Semantics of Natural Language Representations","created":"2022-03-14","cited_by_count":14,"area":null},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2109.07573","title":"Differentiable Physics: A Position Piece","created":"2021-09-14","cited_by_count":12,"area":null},{"id":"2310.14993","title":"Understanding the Inner Workings of Language Models Through Representation Dissimilarity","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2203.07504","title":"VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models","created":"2022-03-14","cited_by_count":10,"area":null},{"id":"2407.09946","title":"Low-Rank Interconnected Adaptation across Layers","created":"2024-07-13","cited_by_count":10,"area":null},{"id":"2504.02862","title":"Towards Understanding How Knowledge Evolves in Large Vision-Language Models","created":"2025-03-31","cited_by_count":10,"area":"mllm"},{"id":"2203.12210","title":"Integrating Vectorized Lexical Constraints for Neural Machine Translation","created":"2022-03-23","cited_by_count":9,"area":null},{"id":"2212.11115","title":"What Makes for Good Tokenizers in Vision Transformer?","created":"2022-12-21","cited_by_count":9,"area":null},{"id":"2303.14871","title":"Coupling Artificial Neurons in BERT and Biological Neurons in the Human Brain","created":"2023-03-27","cited_by_count":9,"area":null},{"id":"2210.07468","title":"Transparency Helps Reveal When Language Models Learn Meaning","created":"2022-10-14","cited_by_count":8,"area":null},{"id":"2303.14956","title":"Unified Text Structuralization with Instruction-tuned Language Models","created":"2023-03-27","cited_by_count":8,"area":null},{"id":"2305.14453","title":"On Robustness of Finetuned Transformer-based NLP Models","created":"2023-05-23","cited_by_count":8,"area":null},{"id":"2305.18294","title":"Transformer Language Models Handle Word Frequency in Prediction Head","created":"2023-05-29","cited_by_count":8,"area":null},{"id":"2309.06054","title":"Breaking through the learning plateaus of in-context learning in Transformer","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2105.07149","title":"DirectQE: Direct Pretraining for Machine Translation Quality Estimation","created":"2021-05-15","cited_by_count":7,"area":null},{"id":"2211.04898","title":"Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2211.09817","title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","created":"2022-11-17","cited_by_count":7,"area":"offlinerl"},{"id":"2407.04151","title":"Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers","created":"2024-07-04","cited_by_count":5,"area":"safety"},{"id":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2603.12298","title":"Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency","created":"2026-03-12","cited_by_count":5,"area":"mechinterp"},{"id":"2604.07569","title":"Learning is Forgetting: LLM Training As Lossy Compression","created":"2026-04-08","cited_by_count":5,"area":null},{"id":"2109.12683","title":"On the Prunability of Attention Heads in Multilingual BERT","created":"2021-09-26","cited_by_count":4,"area":null},{"id":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2205.10238","title":"Visualizing and Explaining Language Models","created":"2022-04-30","cited_by_count":4,"area":null},{"id":"2205.10505","title":"A Study on Transformer Configuration and Training Objective","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2401.11268","title":"Word-Level ASR Quality Estimation for Efficient Corpus Sampling and Post-Editing through Analyzing Attentions of a Reference-Free Metric","created":"2024-01-20","cited_by_count":4,"area":null},{"id":"2410.08250","title":"Exploring ASR-Based Wav2Vec2 for Automated Speech Disorder Assessment: Insights and Analysis","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2502.09245","title":"You Do Not Fully Utilize Transformer's Representation Capacity","created":"2025-02-13","cited_by_count":4,"area":null},{"id":"2506.00382","title":"Spectral Insights into Data-Oblivious Critical Layers in Large Language Models","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2510.21986","title":"Sprint: Sparse-Dense Residual Fusion for Efficient Diffusion Transformers","created":"2025-10-24","cited_by_count":4,"area":"diffusion"},{"id":"2305.12169","title":"Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization","created":"2023-05-20","cited_by_count":3,"area":null},{"id":"2411.06506","title":"CULL-MT: Compression Using Language and Layer pruning for Machine Translation","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2509.08897","title":"Recurrence Meets Transformers for Universal Multimodal Retrieval","created":"2025-09-10","cited_by_count":3,"area":"mllm"},{"id":"2605.17562","title":"Beyond Accuracy: Robustness, Interpretability and Expressiveness of EEG Foundation Models","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2211.07714","title":"Revisiting Attention Weights as Explanations from an Information Theoretic Perspective","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2307.10799","title":"Layer-wise Representation Fusion for Compositional Generalization","created":"2023-07-20","cited_by_count":2,"area":null},{"id":"2403.00869","title":"Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modeling","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2406.09140","title":"Investigating the translation capabilities of Large Language Models trained on parallel data only","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2507.05387","title":"The Generalization Ridge: Information Flow in Natural Language Generation","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2508.18306","title":"SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds","created":"2025-08-23","cited_by_count":2,"area":null},{"id":"2509.23695","title":"Estimating Time Series Foundation Model Transferability via In-Context Learning","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.14262","title":"CAST: Compositional Analysis via Spectral Tracking for Understanding Transformer Layer Functions","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2602.20091","title":"How Retrieved Context Shapes Internal Representations in RAG","created":"2026-02-23","cited_by_count":2,"area":"rag"},{"id":"2112.06733","title":"Measuring Context-Word Biases in Lexical Semantic Datasets","created":"2021-12-13","cited_by_count":1,"area":null}],"next_cursor":"100"}