{"total":120,"rows":[{"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":"2502.09674","title":"The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions","created":"2025-02-13","cited_by_count":41,"area":"lr"},{"id":"2504.08729","title":"Steering CLIP's vision transformer with sparse autoencoders","created":"2025-04-11","cited_by_count":38,"area":"mechinterp"},{"id":"2406.07592","title":"MambaLRP: Explaining Selective State Space Sequence Models","created":"2024-06-11","cited_by_count":32,"area":"ssm"},{"id":"2506.23270","title":"Token Activation Map to Visually Explain Multimodal LLMs","created":"2025-06-29","cited_by_count":32,"area":"mllm"},{"id":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","cited_by_count":25,"area":"mechinterp"},{"id":"2411.11114","title":"JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit","created":"2024-11-17","cited_by_count":22,"area":"safety"},{"id":"2508.21258","title":"RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching","created":"2025-08-28","cited_by_count":13,"area":"mechinterp"},{"id":"2502.14862","title":"Interpretable Text Embeddings and Text Similarity Explanation: A Survey","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2408.12568","title":"Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers","created":"2024-08-22","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2509.17178","title":"Attention Consistency for LLMs Explanation","created":"2025-09-21","cited_by_count":11,"area":null},{"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":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2408.17198","title":"Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features","created":"2024-08-30","cited_by_count":7,"area":null},{"id":"2509.01631","title":"Unraveling LLM Jailbreaks Through Safety Knowledge Neurons","created":"2025-09-01","cited_by_count":7,"area":"safety"},{"id":"2402.12118","title":"Sparse, Efficient and Explainable Data Attribution with DualXDA","created":"2024-02-19","cited_by_count":6,"area":null},{"id":"2406.10479","title":"Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning","created":"2024-06-15","cited_by_count":6,"area":"lr"},{"id":"2506.02138","title":"Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2407.16653","title":"Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models","created":"2024-07-23","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":"2505.17630","title":"Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2506.18985","title":"GLIMPSE: Holistic Cross-Modal Explainability for Large Vision-Language Models","created":"2025-06-23","cited_by_count":5,"area":"mllm"},{"id":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2509.00749","title":"Causal Interpretation of Sparse Autoencoder Features in Vision","created":"2025-08-31","cited_by_count":5,"area":"mechinterp"},{"id":"2509.22415","title":"Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models","created":"2025-09-26","cited_by_count":5,"area":"mllm"},{"id":"2510.14936","title":"Circuit Insights: Towards Interpretability Beyond Activations","created":"2025-10-16","cited_by_count":5,"area":"mechinterp"},{"id":"2504.10906","title":"Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2505.15386","title":"RePPL: Recalibrating Perplexity by Uncertainty in Semantic Propagation and Language Generation for Explainable QA Hallucination Detection","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2507.03197","title":"Quantifying Cross-Attention Interaction in Transformers for Interpreting TCR-pMHC Binding","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2512.07776","title":"GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring","created":"2025-12-08","cited_by_count":4,"area":null},{"id":"2602.06613","title":"DAVE: Distribution-aware Attribution via ViT Gradient Decomposition","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2410.22372","title":"A Hierarchical Language Model For Interpretable Graph Reasoning","created":"2024-10-29","cited_by_count":3,"area":"lr"},{"id":"2503.22399","title":"VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2503.22881","title":"Pairwise Matching of Intermediate Representations for Fine-grained Explainability","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2505.18575","title":"Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2506.13727","title":"Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs","created":"2025-06-16","cited_by_count":3,"area":"mechinterp"},{"id":"2601.17958","title":"TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors","created":"2026-01-25","cited_by_count":3,"area":null},{"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":"2606.16364","title":"Looking Is Not Picking: An Attention-Segment Account of Tool-Selection Failures in LLM Agents","created":"2026-06-15","cited_by_count":3,"area":"agents"},{"id":"2411.12643","title":"DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models","created":"2024-11-19","cited_by_count":2,"area":null},{"id":"2506.03425","title":"A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2512.20514","title":"Explainable time-series forecasting with sampling-free SHAP for Transformers","created":"2025-12-23","cited_by_count":2,"area":null},{"id":"2602.03318","title":"MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"id":"2603.02792","title":"From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors","created":"2026-03-03","cited_by_count":2,"area":null},{"id":"2604.04500","title":"Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward","created":"2026-04-06","cited_by_count":2,"area":"lr"},{"id":"2604.17761","title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","created":"2026-04-20","cited_by_count":2,"area":"mechinterp"},{"id":"2606.00557","title":"Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2410.03296","title":"A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2502.20268","title":"Large Language Models as Attribution Regularizers for Efficient Model Training","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2505.11451","title":"Extracting Explainable Dates From Medical Images By Reverse-Engineering UNIX Timestamps","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2508.15841","title":"A Review of Developmental Interpretability in Large Language Models","created":"2025-08-19","cited_by_count":1,"area":"mechinterp"},{"id":"2510.06070","title":"There is More to Attention: Statistical Filtering Enhances Explanations in Vision Transformers","created":"2025-10-07","cited_by_count":1,"area":null},{"id":"2510.18462","title":"DePass: Unified Feature Attributing by Simple Decomposed Forward Pass","created":"2025-10-21","cited_by_count":1,"area":"mechinterp"},{"id":"2512.18888","title":"Localising Shortcut Learning in Pixel Space via Ordinal Scoring Correlations for Attribution Representations (OSCAR)","created":"2025-12-21","cited_by_count":1,"area":null},{"id":"2601.01446","title":"iFlip: Iterative Feedback-driven Counterfactual Example Refinement","created":"2026-01-04","cited_by_count":1,"area":null},{"id":"2601.05647","title":"Transformer Is Inherently a Causal Learner","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2602.04784","title":"From independent patches to coordinated attention: Controlling information flow in vision transformers","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.16608","title":"Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.21690","title":"Evaluating Post-hoc Explanations of the Transformer-based Genome Language Model DNABERT-2","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.00474","title":"From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models","created":"2026-05-01","cited_by_count":1,"area":"mechinterp"},{"id":"2605.01766","title":"Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time","created":"2026-05-03","cited_by_count":1,"area":"mllm"},{"id":"2605.05285","title":"Attribution-Guided Continual Learning for Large Language Models","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.11885","title":"From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.11906","title":"YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.22168","title":"Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2605.23393","title":"Every Component Is a Lookup: One Linear Graph for Interaction, Composition and Attribution","created":"2026-05-22","cited_by_count":1,"area":"mechinterp"},{"id":"2607.11990","title":"Sparse Inter-Layer Dependencies of Transformer FFN Neurons","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2608.23264","title":"Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2609.38810","title":"CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models","created":"2026-09-30","cited_by_count":1,"area":"mllm"},{"id":"2407.17622","title":"Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans","created":"2024-07-24","cited_by_count":0,"area":null},{"id":"2505.21595","title":"Relevance-driven Input Dropout: an Explanation-guided Regularization Technique","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2509.08963","title":"Value bounds and Convergence Analysis for Averages of LRP attributions","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2509.16479","title":"Thermal Imaging-based Real-time Fall Detection using Motion Flow and Attention-enhanced Convolutional Recurrent Architecture","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2509.25475","title":"TDHook: A Lightweight Framework for Interpretability","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2510.11202","title":"Evaluating Line-level Localization Ability of Learning-based Code Vulnerability Detection Models","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.18810","title":"When LRP Diverges from Leave-One-Out in Transformers","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.00859","title":"Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2512.07010","title":"Always Keep Your Promises: A Model-Agnostic Attribution Algorithm for Neural Networks","created":"2025-12-07","cited_by_count":0,"area":null},{"id":"2601.19672","title":"ProToken: Token-Level Attribution for Federated Large Language Models","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2601.20282","title":"Memory Retrieval in Transformers: Insights from The Encoding Specificity Principle","created":"2026-01-28","cited_by_count":0,"area":"safety"},{"id":"2602.03511","title":"CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrains","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.04607","title":"Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.10234","title":"Why Does It Look There? Structured Explanations for Image Classification","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.15919","title":"Sparse but not Simpler: A Multi-Level Interpretability Analysis of Vision Transformers","created":"2026-03-16","cited_by_count":0,"area":"mechinterp"},{"id":"2603.19742","title":"Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.09368","title":"Through Their Eyes: Fixation-aligned Tuning for Personalized User Emulation","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.14325","title":"Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.13340","title":"Shortcut Mitigation via Spurious-Positive Samples","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.05079","title":"Fast & Faithful Function Vectors","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.09466","title":"DECSELFMASK: Leveraging Unlabeled Text via Self-Relevance-Guided Masking for Decoder-Only Classification","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.19993","title":"Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.21564","title":"LIG: Layer-wise Integrated Gradients for Within-Layer Flow Analysis in Transformers","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.27201","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05356","title":"ReCal3R: Reliability-Calibrated Learning Rates for Streaming 3D Reconstruction","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.07128","title":"Distributed Sparse Interventions in Language Models","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.07716","title":"Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution","created":"2026-07-04","cited_by_count":0,"area":null}],"next_cursor":"100"}