{"total":116,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"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":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"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":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2505.20063","title":"SAEs Are Good for Steering -- If You Select the Right Features","created":"2025-05-26","cited_by_count":78,"area":"mechinterp"},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"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":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55,"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":"2310.14491","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","created":"2023-10-23","cited_by_count":50,"area":"lr"},{"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":"2205.03286","title":"GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers","created":"2022-05-06","cited_by_count":44,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2301.12971","title":"Quantifying Context Mixing in Transformers","created":"2023-01-30","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":"2103.07601","title":"Approximating How Single Head Attention Learns","created":"2021-03-13","cited_by_count":38,"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":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2109.08359","title":"Distilling Linguistic Context for Language Model Compression","created":"2021-09-17","cited_by_count":33,"area":"distill"},{"id":"2302.00456","title":"Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps","created":"2023-02-01","cited_by_count":33,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2306.02873","title":"DecompX: Explaining Transformers Decisions by Propagating Token Decomposition","created":"2023-06-05","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":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","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":"2103.14625","title":"Dodrio: Exploring Transformer Models with Interactive Visualization","created":"2021-03-26","cited_by_count":28,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2305.10010","title":"AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression","created":"2023-05-17","cited_by_count":26,"area":"distill"},{"id":"2310.18969","title":"Analyzing Vision Transformers for Image Classification in Class Embedding Space","created":"2023-10-29","cited_by_count":26,"area":null},{"id":"2104.06709","title":"Towards BERT-based Automatic ICD Coding: Limitations and Opportunities","created":"2021-04-14","cited_by_count":25,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2110.05841","title":"Relative Molecule Self-Attention Transformer","created":"2021-10-12","cited_by_count":21,"area":null},{"id":"2109.13139","title":"Multimodal Integration of Human-Like Attention in Visual Question Answering","created":"2021-09-27","cited_by_count":20,"area":null},{"id":"2101.10044","title":"Cross-lingual Visual Pre-training for Multimodal Machine Translation","created":"2021-01-25","cited_by_count":19,"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":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19,"area":null},{"id":"2206.09355","title":"A Unified Understanding of Deep NLP Models for Text Classification","created":"2022-06-19","cited_by_count":18,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2101.04547","title":"Of Non-Linearity and Commutativity in BERT","created":"2021-01-12","cited_by_count":16,"area":null},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"area":null},{"id":"2305.06754","title":"COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks","created":"2023-05-11","cited_by_count":16,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","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":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"area":null},{"id":"2105.08855","title":"Effective Attention Sheds Light On Interpretability","created":"2021-05-18","cited_by_count":11,"area":null},{"id":"2109.05853","title":"Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions","created":"2021-09-13","cited_by_count":11,"area":null},{"id":"2207.05358","title":"eX-ViT: A Novel eXplainable Vision Transformer for Weakly Supervised Semantic Segmentation","created":"2022-07-12","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":"2403.11894","title":"From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?","created":"2024-03-18","cited_by_count":11,"area":null},{"id":"2207.08466","title":"What does Transformer learn about source code?","created":"2022-07-18","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":"2210.04545","title":"Automatic Evaluation and Analysis of Idioms in Neural Machine Translation","created":"2022-10-10","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":"2405.13536","title":"Attention Mechanisms Don't Learn Additive Models: Rethinking Feature Importance for Transformers","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2506.21812","title":"Towards Transparent AI: A Survey on Explainable Large Language Models","created":"2025-06-26","cited_by_count":7,"area":null},{"id":"2106.05691","title":"Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation","created":"2021-06-10","cited_by_count":6,"area":"distill"},{"id":"2110.08887","title":"Schr\\\"odinger's Tree -- On Syntax and Neural Language Models","created":"2021-10-17","cited_by_count":6,"area":null},{"id":"2209.10876","title":"An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification","created":"2022-09-22","cited_by_count":6,"area":null},{"id":"2406.16955","title":"SRViT: Vision Transformers for Estimating Radar Reflectivity from Satellite Observations at Scale","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2409.07787","title":"Stable Language Model Pre-training by Reducing Embedding Variability","created":"2024-09-12","cited_by_count":6,"area":null},{"id":"2101.06423","title":"Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching","created":"2021-01-16","cited_by_count":5,"area":null},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","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":"2411.16760","title":"LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions","created":"2024-11-24","cited_by_count":5,"area":null},{"id":"2601.05201","title":"Mechanisms of Prompt-Induced Hallucination in Vision-Language Models","created":"2026-01-08","cited_by_count":5,"area":"mllm"},{"id":"2602.01605","title":"Universal Redundancies in Time Series Foundation Models","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2201.11674","title":"Vision Checklist: Towards Testable Error Analysis of Image Models to Help System Designers Interrogate Model Capabilities","created":"2022-01-27","cited_by_count":4,"area":null},{"id":"2203.01146","title":"Controlling the Focus of Pretrained Language Generation Models","created":"2022-03-02","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":"2210.05883","title":"AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2409.12586","title":"Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights","created":"2024-09-19","cited_by_count":4,"area":"distill"},{"id":"2412.11187","title":"Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models","created":"2024-12-15","cited_by_count":4,"area":null},{"id":"2504.01137","title":"Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2509.24837","title":"ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2106.01269","title":"More Identifiable yet Equally Performant Transformers for Text Classification","created":"2021-06-02","cited_by_count":3,"area":null},{"id":"2106.05634","title":"Exploring Unsupervised Pretraining Objectives for Machine Translation","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2306.03598","title":"CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models","created":"2023-06-06","cited_by_count":3,"area":null},{"id":"2311.06928","title":"Attention for Causal Relationship Discovery from Biological Neural Dynamics","created":"2023-11-12","cited_by_count":3,"area":null},{"id":"2505.09861","title":"LiDDA: Data Driven Attribution at LinkedIn","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2509.21631","title":"Towards Transparent AI: A Survey on Explainable Language Models","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2304.06337","title":"Computational modeling of semantic change","created":"2023-04-13","cited_by_count":2,"area":null},{"id":"2402.11896","title":"SIBO: A Simple Booster for Parameter-Efficient Fine-Tuning","created":"2024-02-19","cited_by_count":2,"area":null},{"id":"2504.08712","title":"Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networks","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2511.05064","title":"Order-Level Attention Similarity Across Language Models: A Latent Commonality","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2608.03294","title":"Provably Learning Multi-Head Attention with Queries","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2104.06969","title":"Event Detection as Question Answering with Entity Information","created":"2021-04-14","cited_by_count":1,"area":null},{"id":"2109.05108","title":"Attention-based Contrastive Learning for Winograd Schemas","created":"2021-09-10","cited_by_count":1,"area":null},{"id":"2112.12913","title":"Spoiler in a Textstack: How Much Can Transformers Help?","created":"2021-12-24","cited_by_count":1,"area":null},{"id":"2208.09659","title":"Trigger-free Event Detection via Derangement Reading Comprehension","created":"2022-08-20","cited_by_count":1,"area":null},{"id":"2301.04339","title":"Topics in Contextualised Attention Embeddings","created":"2023-01-11","cited_by_count":1,"area":null},{"id":"2310.13610","title":"Make Your Decision Convincing! A Unified Two-Stage Framework: Self-Attribution and Decision-Making","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2312.07753","title":"Polynomial-based Self-Attention for Table Representation learning","created":"2023-12-12","cited_by_count":1,"area":null},{"id":"2503.16771","title":"Enabling Global, Human-Centered Explanations for LLMs:From Tokens to Interpretable Code and Test Generation","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2602.01893","title":"Geometric Analysis of Token Selection in Multi-Head Attention","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.06302","title":"DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models","created":"2026-03-06","cited_by_count":1,"area":"mllm"},{"id":"2604.10949","title":"Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models","created":"2026-04-13","cited_by_count":1,"area":"lr"},{"id":"2106.11740","title":"LV-BERT: Exploiting Layer Variety for BERT","created":"2021-06-22","cited_by_count":0,"area":null}],"next_cursor":"100"}