{"total":189,"rows":[{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601,"area":null},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361,"area":null},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"area":null},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2504.02732","title":"Why do LLMs attend to the first token?","created":"2025-04-03","cited_by_count":127,"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":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2303.04245","title":"How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding","created":"2023-03-07","cited_by_count":86,"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":"2402.16061","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","created":"2024-02-25","cited_by_count":64,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","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":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50,"area":null},{"id":"2212.10020","title":"On the Blind Spots of Model-Based Evaluation Metrics for Text Generation","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2402.11917","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","created":"2024-02-19","cited_by_count":49,"area":null},{"id":"2202.04903","title":"Investigating Explainability of Generative AI for Code through Scenario-based Design","created":"2022-02-10","cited_by_count":47,"area":null},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","cited_by_count":44,"area":null},{"id":"2304.06248","title":"LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model","created":"2023-04-13","cited_by_count":43,"area":null},{"id":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41,"area":null},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2402.02364","title":"Loss Landscape Degeneracy and Stagewise Development in Transformers","created":"2024-02-04","cited_by_count":40,"area":null},{"id":"2402.04161","title":"Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains","created":"2024-02-06","cited_by_count":40,"area":null},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2212.07850","title":"Attention as a Guide for Simultaneous Speech Translation","created":"2022-12-15","cited_by_count":32,"area":null},{"id":"2305.13417","title":"VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers","created":"2023-05-22","cited_by_count":32,"area":null},{"id":"2312.00751","title":"Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals","created":"2023-12-01","cited_by_count":32,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2502.12170","title":"MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections","created":"2025-02-13","cited_by_count":31,"area":null},{"id":"2312.01429","title":"Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars","created":"2023-12-03","cited_by_count":30,"area":null},{"id":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29,"area":null},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29,"area":null},{"id":"2306.02295","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","created":"2023-06-04","cited_by_count":29,"area":null},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2204.12130","title":"LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models","created":"2022-04-26","cited_by_count":28,"area":null},{"id":"2104.12874","title":"Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention","created":"2021-04-26","cited_by_count":27,"area":null},{"id":"2206.12279","title":"AnyMorph: Learning Transferable Polices By Inferring Agent Morphology","created":"2022-06-17","cited_by_count":27,"area":null},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26,"area":null},{"id":"2405.20131","title":"Language Models Need Inductive Biases to Count Inductively","created":"2024-05-30","cited_by_count":25,"area":null},{"id":"2301.02240","title":"Skip-Attention: Improving Vision Transformers by Paying Less Attention","created":"2023-01-05","cited_by_count":24,"area":null},{"id":"2402.13449","title":"CAMELoT: Towards Large Language Models with Training-Free Consolidated Associative Memory","created":"2024-02-21","cited_by_count":24,"area":null},{"id":"2305.16093","title":"End-to-End Simultaneous Speech Translation with Differentiable Segmentation","created":"2023-05-25","cited_by_count":22,"area":null},{"id":"2101.00196","title":"On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification","created":"2021-01-01","cited_by_count":21,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2504.10063","title":"Hallucination Detection in LLMs with Topological Divergence on Attention Graphs","created":"2025-04-14","cited_by_count":19,"area":null},{"id":"2310.04861","title":"Uncovering hidden geometry in Transformers via disentangling position and context","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2305.16784","title":"Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization","created":"2023-05-26","cited_by_count":17,"area":null},{"id":"2412.11965","title":"Inferring Functionality of Attention Heads from their Parameters","created":"2024-12-16","cited_by_count":17,"area":null},{"id":"2102.12702","title":"LazyFormer: Self Attention with Lazy Update","created":"2021-02-25","cited_by_count":16,"area":null},{"id":"2108.08375","title":"Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks","created":"2021-08-18","cited_by_count":16,"area":null},{"id":"2407.10488","title":"How and where does CLIP process negation?","created":"2024-07-15","cited_by_count":16,"area":null},{"id":"2408.09121","title":"Selective Prompt Anchoring for Code Generation","created":"2024-08-17","cited_by_count":16,"area":null},{"id":"2309.01826","title":"One Wide Feedforward is All You Need","created":"2023-09-04","cited_by_count":15,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2402.16998","title":"What Do Language Models Hear? Probing for Auditory Representations in Language Models","created":"2024-02-26","cited_by_count":15,"area":null},{"id":"2106.01335","title":"On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2401.12947","title":"Transformer-Based Models Are Not Yet Perfect At Learning to Emulate Structural Recursion","created":"2024-01-23","cited_by_count":14,"area":null},{"id":"2410.16139","title":"A Psycholinguistic Evaluation of Language Models' Sensitivity to Argument Roles","created":"2024-10-21","cited_by_count":14,"area":null},{"id":"2410.18819","title":"From Imitation to Introspection: Probing Self-Consciousness in Language Models","created":"2024-10-24","cited_by_count":14,"area":null},{"id":"2507.02550","title":"Position: A Theory of Deep Learning Must Include Compositional Sparsity","created":"2025-07-03","cited_by_count":14,"area":null},{"id":"2212.03597","title":"DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing","created":"2022-12-07","cited_by_count":13,"area":null},{"id":"2101.00371","title":"On-the-Fly Attention Modulation for Neural Generation","created":"2021-01-02","cited_by_count":12,"area":null},{"id":"2311.04354","title":"Uncovering Intermediate Variables in Transformers using Circuit Probing","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2105.08855","title":"Effective Attention Sheds Light On Interpretability","created":"2021-05-18","cited_by_count":11,"area":null},{"id":"2205.09295","title":"Are Prompt-based Models Clueless?","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11,"area":null},{"id":"2311.13541","title":"Linear Log-Normal Attention with Unbiased Concentration","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2402.03485","title":"Attention Meets Post-hoc Interpretability: A Mathematical Perspective","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2411.06171","title":"SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models","created":"2024-11-09","cited_by_count":11,"area":null},{"id":"2503.11302","title":"Are formal and functional linguistic mechanisms dissociated in language models?","created":"2025-03-14","cited_by_count":11,"area":null},{"id":"2407.12866","title":"Beyond KV Caching: Shared Attention for Efficient LLMs","created":"2024-07-13","cited_by_count":10,"area":null},{"id":"2205.10828","title":"What Do Compressed Multilingual Machine Translation Models Forget?","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2207.06897","title":"Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language","created":"2022-07-14","cited_by_count":9,"area":null},{"id":"2310.10318","title":"Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2501.01059","title":"Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2405.14161","title":"Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models","created":"2024-05-23","cited_by_count":8,"area":null},{"id":"2407.01646","title":"ESALE: Enhancing Code-Summary Alignment Learning for Source Code Summarization","created":"2024-07-01","cited_by_count":8,"area":null},{"id":"2502.13179","title":"PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models","created":"2025-02-18","cited_by_count":8,"area":null},{"id":"2109.05748","title":"GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2205.03759","title":"Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information","created":"2022-05-08","cited_by_count":7,"area":null},{"id":"2310.19084","title":"Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention","created":"2023-10-29","cited_by_count":7,"area":null},{"id":"2406.13762","title":"Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2406.13770","title":"Elliptical Attention","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2410.09457","title":"Power-Softmax: Towards Secure LLM Inference over Encrypted Data","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2105.14668","title":"On the Interplay Between Fine-tuning and Composition in Transformers","created":"2021-05-31","cited_by_count":6,"area":null},{"id":"2105.14940","title":"Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?","created":"2021-05-31","cited_by_count":6,"area":null},{"id":"2106.08823","title":"Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2110.06063","title":"MEDUSA: Multi-scale Encoder-Decoder Self-Attention Deep Neural Network Architecture for Medical Image Analysis","created":"2021-10-12","cited_by_count":6,"area":null},{"id":"2112.05364","title":"Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation","created":"2021-12-10","cited_by_count":6,"area":null},{"id":"2204.02922","title":"Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding","created":"2022-04-06","cited_by_count":6,"area":null},{"id":"2210.04633","title":"CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure","created":"2022-10-07","cited_by_count":6,"area":null},{"id":"2410.00131","title":"Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2104.12847","title":"Morph Call: Probing Morphosyntactic Content of Multilingual Transformers","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2210.05506","title":"Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration","created":"2022-10-11","cited_by_count":5,"area":null},{"id":"2211.06420","title":"The Architectural Bottleneck Principle","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2311.08902","title":"On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series","created":"2023-11-15","cited_by_count":5,"area":null},{"id":"2312.06034","title":"Modeling Uncertainty in Personalized Emotion Prediction with Normalizing Flows","created":"2023-12-10","cited_by_count":5,"area":null}],"next_cursor":"100"}