{"total":35,"rows":[{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","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":"2305.11746","title":"HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation","created":"2023-05-19","cited_by_count":35,"area":null},{"id":"2112.08802","title":"UNIREX: A Unified Learning Framework for Language Model Rationale Extraction","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"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":"2203.09258","title":"Explainability in Graph Neural Networks: An Experimental Survey","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2305.13386","title":"Can LLMs facilitate interpretation of pre-trained language models?","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2102.01792","title":"A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks","created":"2021-02-02","cited_by_count":14,"area":null},{"id":"2101.11310","title":"Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling","created":"2021-01-27","cited_by_count":13,"area":null},{"id":"2310.11884","title":"From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2305.17073","title":"NeuroX Library for Neuron Analysis of Deep NLP Models","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2210.08478","title":"Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","cited_by_count":8,"area":null},{"id":"2306.06205","title":"Morphosyntactic probing of multilingual BERT models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2104.08793","title":"SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning","created":"2021-04-18","cited_by_count":7,"area":null},{"id":"2205.12542","title":"ER-Test: Evaluating Explanation Regularization Methods for Language Models","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2309.10291","title":"Koopman Invertible Autoencoder: Leveraging Forward and Backward Dynamics for Temporal Modeling","created":"2023-09-19","cited_by_count":6,"area":null},{"id":"2201.06384","title":"Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations","created":"2022-01-17","cited_by_count":5,"area":null},{"id":"2201.08214","title":"A Latent-Variable Model for Intrinsic Probing","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2308.05219","title":"Decoding Layer Saliency in Language Transformers","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2105.08039","title":"Fine-grained Interpretation and Causation Analysis in Deep NLP Models","created":"2021-05-17","cited_by_count":4,"area":null},{"id":"2102.08634","title":"On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification","created":"2021-02-17","cited_by_count":3,"area":null},{"id":"2202.02516","title":"A Survey on Automated Sarcasm Detection on Twitter","created":"2022-02-05","cited_by_count":3,"area":null},{"id":"2311.08240","title":"Investigating the Encoding of Words in BERT's Neurons using Feature Textualization","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2406.16672","title":"CAVE: Controllable Authorship Verification Explanations","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2106.04935","title":"Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2109.00521","title":"Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques","created":"2021-09-01","cited_by_count":2,"area":null},{"id":"2303.03019","title":"NxPlain: Web-based Tool for Discovery of Latent Concepts","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2401.16731","title":"Towards Generating Informative Textual Description for Neurons in Language Models","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2103.03108","title":"An empirical analysis of phrase-based and neural machine translation","created":"2021-03-04","cited_by_count":0,"area":null}],"next_cursor":null}