{"total":12,"rows":[{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"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":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16,"area":null},{"id":"2408.11843","title":"Identifying and Mitigating Social Bias Knowledge in Language Models","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2203.10166","title":"Concept-based Adversarial Attacks: Tricking Humans and Classifiers Alike","created":"2022-03-18","cited_by_count":3,"area":null},{"id":"2312.06887","title":"Understanding and Leveraging the Learning Phases of Neural Networks","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2406.10962","title":"SynthTree: Co-supervised Local Model Synthesis for Explainable Prediction","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2102.05917","title":"PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification","created":"2021-02-11","cited_by_count":1,"area":null},{"id":"2106.06057","title":"Domain Transformer: Predicting Samples of Unseen, Future Domains","created":"2021-06-10","cited_by_count":0,"area":null},{"id":"2202.08299","title":"The learning phases in NN: From Fitting the Majority to Fitting a Few","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2510.06541","title":"Cluster Paths: Navigating Interpretability in Neural Networks","created":"2025-10-08","cited_by_count":0,"area":null}],"next_cursor":null}