{"total":292,"rows":[{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716,"area":null},{"id":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367,"area":null},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2402.18815","title":"How do Large Language Models Handle Multilingualism?","created":"2024-02-29","cited_by_count":150,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"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":"2312.04985","title":"SparQ Attention: Bandwidth-Efficient LLM Inference","created":"2023-12-08","cited_by_count":119,"area":"inference"},{"id":"2502.09838","title":"HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation","created":"2025-02-14","cited_by_count":114,"area":"mllm"},{"id":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108,"area":"mechinterp"},{"id":"2112.14168","title":"A Survey on Gender Bias in Natural Language Processing","created":"2021-12-28","cited_by_count":89,"area":null},{"id":"2103.15049","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","created":"2021-03-28","cited_by_count":87,"area":null},{"id":"2110.02467","title":"BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models","created":"2021-10-06","cited_by_count":85,"area":"safety"},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83,"area":"rag"},{"id":"2407.21124","title":"Zero Shot Health Trajectory Prediction Using Transformer","created":"2024-07-30","cited_by_count":77,"area":null},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"area":null},{"id":"2203.08383","title":"Iteratively Prompt Pre-trained Language Models for Chain of Thought","created":"2022-03-16","cited_by_count":75,"area":"lr"},{"id":"2406.15765","title":"Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration","created":"2024-06-22","cited_by_count":74,"area":null},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73,"area":null},{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72,"area":"safety"},{"id":"2208.07852","title":"Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models","created":"2022-08-16","cited_by_count":70,"area":null},{"id":"2203.08411","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","created":"2022-03-16","cited_by_count":64,"area":null},{"id":"2104.04167","title":"The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation","created":"2021-04-09","cited_by_count":61,"area":null},{"id":"2209.14557","title":"Neural Media Bias Detection Using Distant Supervision With BABE -- Bias Annotations By Experts","created":"2022-09-29","cited_by_count":56,"area":null},{"id":"2305.01579","title":"Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise","created":"2023-05-02","cited_by_count":54,"area":"rag"},{"id":"2202.01338","title":"Regression Transformer: Concurrent sequence regression and generation for molecular language modeling","created":"2022-02-01","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":"2209.14803","title":"polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics","created":"2022-09-29","cited_by_count":48,"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":"2402.13055","title":"Identifying Semantic Induction Heads to Understand In-Context Learning","created":"2024-02-20","cited_by_count":47,"area":null},{"id":"2101.11131","title":"CLiMP: A Benchmark for Chinese Language Model Evaluation","created":"2021-01-26","cited_by_count":46,"area":null},{"id":"2203.00131","title":"A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark","created":"2022-02-28","cited_by_count":45,"area":null},{"id":"2201.09745","title":"Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks","created":"2022-01-24","cited_by_count":42,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2407.10114","title":"TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation","created":"2024-07-14","cited_by_count":42,"area":null},{"id":"2401.16765","title":"A Cross-Language Investigation into Jailbreak Attacks in Large Language Models","created":"2024-01-30","cited_by_count":41,"area":"safety"},{"id":"2204.10688","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","created":"2022-04-22","cited_by_count":40,"area":null},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","cited_by_count":38,"area":null},{"id":"2310.13121","title":"Understanding Addition in Transformers","created":"2023-10-19","cited_by_count":34,"area":null},{"id":"2203.00054","title":"LISA: Learning Interpretable Skill Abstractions from Language","created":"2022-02-28","cited_by_count":30,"area":"offlinerl"},{"id":"2303.13731","title":"How Does Attention Work in Vision Transformers? A Visual Analytics Attempt","created":"2023-03-24","cited_by_count":30,"area":null},{"id":"2103.14625","title":"Dodrio: Exploring Transformer Models with Interactive Visualization","created":"2021-03-26","cited_by_count":28,"area":null},{"id":"2210.14188","title":"MOFormer: Self-Supervised Transformer model for Metal-Organic Framework Property Prediction","created":"2022-10-25","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":"2208.00636","title":"Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writing","created":"2022-08-01","cited_by_count":27,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2301.02240","title":"Skip-Attention: Improving Vision Transformers by Paying Less Attention","created":"2023-01-05","cited_by_count":24,"area":null},{"id":"2407.15248","title":"XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models","created":"2024-07-21","cited_by_count":23,"area":null},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2104.05947","title":"\"Subverting the Jewtocracy\": Online Antisemitism Detection Using Multimodal Deep Learning","created":"2021-04-13","cited_by_count":21,"area":null},{"id":"2103.00213","title":"Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention","created":"2021-02-27","cited_by_count":20,"area":null},{"id":"2305.02549","title":"FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction","created":"2023-05-04","cited_by_count":20,"area":null},{"id":"2104.00926","title":"VisQA: X-raying Vision and Language Reasoning in Transformers","created":"2021-04-02","cited_by_count":19,"area":null},{"id":"2303.11126","title":"Robustifying Token Attention for Vision Transformers","created":"2023-03-20","cited_by_count":19,"area":null},{"id":"2307.05390","title":"CrysMMNet: Multimodal Representation for Crystal Property Prediction","created":"2023-06-09","cited_by_count":18,"area":null},{"id":"2111.01582","title":"LMdiff: A Visual Diff Tool to Compare Language Models","created":"2021-11-02","cited_by_count":17,"area":null},{"id":"2311.13857","title":"Challenges of Large Language Models for Mental Health Counseling","created":"2023-11-23","cited_by_count":17,"area":null},{"id":"2505.24333","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","created":"2025-05-30","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":"2104.03656","title":"How Transferable are Reasoning Patterns in VQA?","created":"2021-04-08","cited_by_count":16,"area":null},{"id":"2104.08942","title":"Attention-based Clinical Note Summarization","created":"2021-04-18","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":"2205.10036","title":"Exploring Extreme Parameter Compression for Pre-trained Language Models","created":"2022-05-20","cited_by_count":15,"area":null},{"id":"2209.08721","title":"Joint Language Semantic and Structure Embedding for Knowledge Graph Completion","created":"2022-09-19","cited_by_count":15,"area":null},{"id":"2403.09053","title":"Towards a theory of model distillation","created":"2024-03-14","cited_by_count":15,"area":null},{"id":"2405.15302","title":"Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism","created":"2024-05-24","cited_by_count":15,"area":"lr"},{"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":"2107.00175","title":"Elbert: Fast Albert with Confidence-Window Based Early Exit","created":"2021-07-01","cited_by_count":14,"area":"inference"},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2210.04172","title":"A Transformer-based deep neural network model for SSVEP classification","created":"2022-10-09","cited_by_count":14,"area":null},{"id":"2309.14488","title":"When Automated Assessment Meets Automated Content Generation: Examining Text Quality in the Era of GPTs","created":"2023-09-25","cited_by_count":13,"area":null},{"id":"2311.14126","title":"Towards Auditing Large Language Models: Improving Text-based Stereotype Detection","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2204.10200","title":"An Exploratory Study on Code Attention in BERT","created":"2022-04-05","cited_by_count":12,"area":null},{"id":"2303.12364","title":"ExBEHRT: Extended Transformer for Electronic Health Records to Predict Disease Subtypes & Progressions","created":"2023-03-22","cited_by_count":12,"area":null},{"id":"2312.15033","title":"Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention","created":"2023-12-22","cited_by_count":12,"area":null},{"id":"2501.15674","title":"TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMs","created":"2025-01-26","cited_by_count":12,"area":"lr"},{"id":"2108.13587","title":"T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP","created":"2021-08-31","cited_by_count":11,"area":null},{"id":"2109.04738","title":"On the validity of pre-trained transformers for natural language processing in the software engineering domain","created":"2021-09-10","cited_by_count":11,"area":null},{"id":"2110.10185","title":"GenNI: Human-AI Collaboration for Data-Backed Text Generation","created":"2021-10-19","cited_by_count":11,"area":null},{"id":"2405.16042","title":"Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention","created":"2024-05-25","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2504.05445","title":"Probing the Visualization Literacy of Vision Language Models: the Good, the Bad, and the Ugly","created":"2025-04-07","cited_by_count":11,"area":"mllm"},{"id":"2209.13220","title":"Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning","created":"2022-09-27","cited_by_count":10,"area":null},{"id":"2212.03044","title":"On the Importance of Clinical Notes in Multi-modal Learning for EHR Data","created":"2022-12-06","cited_by_count":10,"area":null},{"id":"2401.08376","title":"KADEL: Knowledge-Aware Denoising Learning for Commit Message Generation","created":"2024-01-16","cited_by_count":10,"area":null},{"id":"2412.08258","title":"Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Field","created":"2024-12-11","cited_by_count":10,"area":null},{"id":"2502.11244","title":"Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment","created":"2025-02-16","cited_by_count":10,"area":"alignment"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2103.10674","title":"Learning Multiscale Correlations for Human Motion Prediction","created":"2021-03-19","cited_by_count":9,"area":null},{"id":"2103.10825","title":"Variational Knowledge Distillation for Disease Classification in Chest X-Rays","created":"2021-03-19","cited_by_count":9,"area":"distill"},{"id":"2112.07165","title":"Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2210.05709","title":"Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers","created":"2022-10-11","cited_by_count":9,"area":null},{"id":"2301.04528","title":"The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2301.04704","title":"SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2410.21717","title":"Generating Realistic Tabular Data with Large Language Models","created":"2024-10-29","cited_by_count":9,"area":null},{"id":"2106.01536","title":"BERT meets LIWC: Exploring State-of-the-Art Language Models for Predicting Communication Behavior in Couples' Conflict Interactions","created":"2021-06-03","cited_by_count":8,"area":null},{"id":"2109.02797","title":"Puzzle Solving without Search or Human Knowledge: An Unnatural Language Approach","created":"2021-09-07","cited_by_count":8,"area":null}],"next_cursor":"100"}