{"list":"other","total":52,"rows":[{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1903.03894","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","created":"2019-03-10","cited_by_count":737},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2205.12446","title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech","created":"2022-05-25","cited_by_count":469},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","created":"2019-01-20","cited_by_count":252},{"id":"1312.5663","title":"k-Sparse Autoencoders","created":"2013-12-19","cited_by_count":215},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"2503.03321","title":"See What You Are Told: Visual Attention Sink in Large Multimodal Models","created":"2025-03-05","cited_by_count":132},{"id":"2206.11104","title":"OpenXAI: Towards a Transparent Evaluation of Model Explanations","created":"2022-06-22","cited_by_count":126},{"id":"2410.07149","title":"Towards Interpreting Visual Information Processing in Vision-Language Models","created":"2024-10-09","cited_by_count":122},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"id":"2402.04614","title":"Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models","created":"2024-02-07","cited_by_count":105},{"id":"1902.02181","title":"Attention in Natural Language Processing","created":"2019-02-04","cited_by_count":101},{"id":"2208.09339","title":"Evaluating Explainability for Graph Neural Networks","created":"2022-08-19","cited_by_count":87},{"id":"2405.08366","title":"Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control","created":"2024-05-14","cited_by_count":86},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76},{"id":"2408.14512","title":"LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings","created":"2024-08-25","cited_by_count":61},{"id":"2203.06877","title":"Rethinking Stability for Attribution-based Explanations","created":"2022-03-14","cited_by_count":52},{"id":"2102.05228","title":"Towards Better Explanations of Class Activation Mapping","created":"2021-02-10","cited_by_count":47},{"id":"2106.09078","title":"Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods","created":"2021-06-16","cited_by_count":36},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34},{"id":"2502.12084","title":"VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues","created":"2025-02-17","cited_by_count":33},{"id":"2107.08264","title":"M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis","created":"2021-07-17","cited_by_count":29},{"id":"2303.10667","title":"Audio-Text Models Do Not Yet Leverage Natural Language","created":"2023-03-19","cited_by_count":26},{"id":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","cited_by_count":25},{"id":"2503.11667","title":"LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models","created":"2025-02-24","cited_by_count":23},{"id":"2412.15828","title":"Measuring Cross-Modal Interactions in Multimodal Models","created":"2024-12-20","cited_by_count":16},{"id":"2405.12522","title":"Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models","created":"2024-05-21","cited_by_count":15},{"id":"2103.01616","title":"Interpretable Multi-Modal Hate Speech Detection","created":"2021-03-02","cited_by_count":10},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9},{"id":"2001.01037","title":"Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models","created":"2020-01-04","cited_by_count":8},{"id":"2412.20622","title":"Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models","created":"2024-12-29","cited_by_count":4},{"id":"1712.06228","title":"Visual Explanations from Hadamard Product in Multimodal Deep Networks","created":"2017-12-18","cited_by_count":3}],"next_cursor":null}