{"total":60,"rows":[{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388,"area":"lr"},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78,"area":null},{"id":"2111.07367","title":"\"Will You Find These Shortcuts?\" A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification","created":"2021-11-14","cited_by_count":66,"area":null},{"id":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37,"area":null},{"id":"2103.11072","title":"Local Interpretations for Explainable Natural Language Processing: A Survey","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2110.08412","title":"Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining","created":"2021-10-15","cited_by_count":31,"area":null},{"id":"2305.09770","title":"ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing","created":"2023-05-16","cited_by_count":31,"area":null},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"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,"area":null},{"id":"2109.02738","title":"Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica","created":"2021-09-06","cited_by_count":23,"area":null},{"id":"2106.04016","title":"Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering","created":"2021-06-08","cited_by_count":20,"area":null},{"id":"2410.12409","title":"Revealing the Barriers of Language Agents in Planning","created":"2024-10-16","cited_by_count":20,"area":"agents"},{"id":"2104.10283","title":"GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering","created":"2021-04-20","cited_by_count":16,"area":null},{"id":"2102.05951","title":"Text Compression-aided Transformer Encoding","created":"2021-02-11","cited_by_count":13,"area":null},{"id":"2210.04497","title":"Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation","created":"2022-10-10","cited_by_count":13,"area":null},{"id":"2110.08419","title":"Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding","created":"2021-10-16","cited_by_count":12,"area":null},{"id":"2409.17455","title":"Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2104.08763","title":"Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training","created":"2021-04-18","cited_by_count":8,"area":null},{"id":"2109.00928","title":"Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2204.06239","title":"Can Question Rewriting Help Conversational Question Answering?","created":"2022-04-13","cited_by_count":8,"area":null},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","cited_by_count":8,"area":null},{"id":"2401.18001","title":"Desiderata for the Context Use of Question Answering Systems","created":"2024-01-31","cited_by_count":7,"area":null},{"id":"2109.11728","title":"AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses","created":"2021-09-24","cited_by_count":5,"area":null},{"id":"2210.13391","title":"Explaining Translationese: why are Neural Classifiers Better and what do they Learn?","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2211.04780","title":"On the Robustness of Explanations of Deep Neural Network Models: A Survey","created":"2022-11-09","cited_by_count":5,"area":null},{"id":"2212.10392","title":"Debiasing Stance Detection Models with Counterfactual Reasoning and Adversarial Bias Learning","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2303.14920","title":"Adapting Pretrained Language Models for Solving Tabular Prediction Problems in the Electronic Health Record","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2310.07819","title":"Faithfulness Measurable Masked Language Models","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2211.02646","title":"Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2209.09146","title":"Semantic-based Pre-training for Dialogue Understanding","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2210.07469","title":"StyLEx: Explaining Style Using Human Lexical Annotations","created":"2022-10-14","cited_by_count":3,"area":null},{"id":"2305.09400","title":"Consistent Multi-Granular Rationale Extraction for Explainable Multi-hop Fact Verification","created":"2023-05-16","cited_by_count":3,"area":null},{"id":"2306.11386","title":"Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2308.07937","title":"Automated Testing and Improvement of Named Entity Recognition Systems","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2310.04821","title":"A New Baseline Assumption of Integated Gradients Based on Shaply value","created":"2023-10-07","cited_by_count":3,"area":null},{"id":"2408.11252","title":"Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models","created":"2024-08-21","cited_by_count":3,"area":null},{"id":"2102.03016","title":"Model Agnostic Answer Reranking System for Adversarial Question Answering","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2109.00077","title":"Interactive Machine Comprehension with Dynamic Knowledge Graphs","created":"2021-08-31","cited_by_count":2,"area":null},{"id":"2309.09380","title":"Mitigating Shortcuts in Language Models with Soft Label Encoding","created":"2023-09-17","cited_by_count":2,"area":null},{"id":"2401.00751","title":"Machine Translation Testing via Syntactic Tree Pruning","created":"2024-01-01","cited_by_count":2,"area":null},{"id":"2404.11276","title":"Towards Data-Centric Automatic R&D","created":"2024-04-17","cited_by_count":2,"area":null},{"id":"2506.07446","title":"Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2201.01080","title":"Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial Detection","created":"2022-01-04","cited_by_count":1,"area":null},{"id":"2508.03713","title":"Tell Me Without Telling Me: Two-Way Prediction of Visualization Literacy and Visual Attention","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2101.05624","title":"Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification","created":"2021-01-10","cited_by_count":0,"area":null},{"id":"2104.02851","title":"Interpreting A Pre-trained Model Is A Key For Model Architecture Optimization: A Case Study On Wav2Vec 2.0","created":"2021-04-07","cited_by_count":0,"area":null},{"id":"2108.12585","title":"On the Significance of Question Encoder Sequence Model in the Out-of-Distribution Performance in Visual Question Answering","created":"2021-08-28","cited_by_count":0,"area":null},{"id":"2111.05108","title":"\"How Does It Detect A Malicious App?\" Explaining the Predictions of AI-based Android Malware Detector","created":"2021-11-06","cited_by_count":0,"area":null},{"id":"2112.00245","title":"True or False: Does the Deep Learning Model Learn to Detect Rumors?","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2207.08943","title":"MRCLens: an MRC Dataset Bias Detection Toolkit","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2211.04364","title":"NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?","created":"2022-11-08","cited_by_count":0,"area":null},{"id":"2211.16093","title":"Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2406.19642","title":"IDT: Dual-Task Adversarial Attacks for Privacy Protection","created":"2024-06-28","cited_by_count":0,"area":"safety"},{"id":"2411.06213","title":"Incorporating Human Explanations for Robust Hate Speech Detection","created":"2024-11-09","cited_by_count":0,"area":null}],"next_cursor":null}