{"list":"other","total":78,"rows":[{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1807.00431","title":"Confounding variables can degrade generalization performance of radiological deep learning models","created":"2018-07-02","cited_by_count":379},{"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":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2004.03061","title":"Information-Theoretic Probing for Linguistic Structure","created":"2020-04-07","cited_by_count":207},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2004.12265","title":"Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias","created":"2020-04-26","cited_by_count":191},{"id":"2503.08679","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","created":"2025-03-11","cited_by_count":170},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156},{"id":"2005.00719","title":"Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?","created":"2020-05-02","cited_by_count":151},{"id":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108},{"id":"1703.10631","title":"Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention","created":"2017-03-30","cited_by_count":107},{"id":"1812.03789","title":"Abstracting Causal Models","created":"2018-12-10","cited_by_count":107},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83},{"id":"2305.13673","title":"Physics of Language Models: Part 1, Learning Hierarchical Language Structures","created":"2023-05-23","cited_by_count":83},{"id":"2311.17030","title":"Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching","created":"2023-11-28","cited_by_count":80},{"id":"2212.11870","title":"Impossibility Theorems for Feature Attribution","created":"2022-12-22","cited_by_count":78},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75},{"id":"2305.17553","title":"Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark","created":"2023-05-27","cited_by_count":62},{"id":"2002.09595","title":"The Pragmatic Turn in Explainable Artificial Intelligence (XAI)","created":"2020-02-22","cited_by_count":54},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37},{"id":"2502.20914","title":"Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?","created":"2025-02-28","cited_by_count":34},{"id":"2501.17727","title":"Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers","created":"2025-01-29","cited_by_count":30},{"id":"2410.13032","title":"Hypothesis Testing the Circuit Hypothesis in LLMs","created":"2024-10-16","cited_by_count":29},{"id":"2106.02559","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","created":"2021-06-04","cited_by_count":28},{"id":"2207.02598","title":"Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning","created":"2022-07-06","cited_by_count":26},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24},{"id":"1511.01863","title":"Can parametric statistical methods be trusted for fMRI based group studies?","created":"2015-11-05","cited_by_count":22},{"id":"2405.06800","title":"LLM-Generated Black-box Explanations Can Be Adversarially Helpful","created":"2024-05-10","cited_by_count":21},{"id":"1810.13373","title":"Analyzing biological and artificial neural networks: challenges with opportunities for synergy?","created":"2018-10-31","cited_by_count":20},{"id":"2009.07364","title":"An information theoretic view on selecting linguistic probes","created":"2020-09-15","cited_by_count":19},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17},{"id":"2510.00845","title":"Mechanistic Interpretability as Statistical Estimation: A Variance Analysis","created":"2025-10-01","cited_by_count":15},{"id":"2404.03713","title":"Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors","created":"2024-04-04","cited_by_count":13},{"id":"2408.05859","title":"The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms","created":"2024-08-11","cited_by_count":13},{"id":"2505.16004","title":"Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders","created":"2025-05-21","cited_by_count":12},{"id":"2408.15510","title":"How Reliable are Causal Probing Interventions?","created":"2024-08-28","cited_by_count":11},{"id":"2205.10119","title":"Is explainable AI a race against model complexity?","created":"2022-05-17","cited_by_count":9},{"id":"2502.19964","title":"Do Sparse Autoencoders Generalize? A Case Study of Answerability","created":"2025-02-27","cited_by_count":8},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8},{"id":"1907.06374","title":"What does it mean to understand a neural network?","created":"2019-07-15","cited_by_count":4},{"id":"2506.04237","title":"A Comprehensive Survey on the Risks and Limitations of Concept-based Models","created":"2025-05-25","cited_by_count":4},{"id":"2507.23535","title":"Transparent AI: The Case for Interpretability and Explainability","created":"2025-07-31","cited_by_count":3},{"id":"1710.03390","title":"On Preemption and Overdetermination in Formal Theories of Causality","created":"2017-10-10","cited_by_count":1},{"id":"2312.08063","title":"Estimation of Concept Explanations Should be Uncertainty Aware","created":"2023-12-13","cited_by_count":1}],"next_cursor":null}