{"total":140,"rows":[{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2306.01941","title":"AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap","created":"2023-06-02","cited_by_count":123,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2104.08455","title":"Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding","created":"2021-04-17","cited_by_count":106,"area":null},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100,"area":null},{"id":"2305.01904","title":"Robust Multi-bit Natural Language Watermarking through Invariant Features","created":"2023-05-03","cited_by_count":82,"area":"safety"},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2202.08816","title":"Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning","created":"2022-02-17","cited_by_count":79,"area":null},{"id":"2302.13942","title":"Inseq: An Interpretability Toolkit for Sequence Generation Models","created":"2023-02-27","cited_by_count":78,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"id":"2101.03453","title":"BERT & Family Eat Word Salad: Experiments with Text Understanding","created":"2021-01-10","cited_by_count":44,"area":null},{"id":"2301.07779","title":"Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection","created":"2023-01-18","cited_by_count":44,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"area":null},{"id":"2307.16630","title":"Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks","created":"2023-07-31","cited_by_count":34,"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":"2104.08782","title":"On the Sensitivity and Stability of Model Interpretations in NLP","created":"2021-04-18","cited_by_count":30,"area":null},{"id":"2105.14652","title":"Attention Flows are Shapley Value Explanations","created":"2021-05-31","cited_by_count":30,"area":null},{"id":"2208.12852","title":"What Do NLP Researchers Believe? Results of the NLP Community Metasurvey","created":"2022-08-26","cited_by_count":28,"area":null},{"id":"2109.06387","title":"Rationales for Sequential Predictions","created":"2021-09-14","cited_by_count":26,"area":null},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2403.09346","title":"B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions","created":"2024-03-14","cited_by_count":26,"area":"mllm"},{"id":"2111.05711","title":"Counterfactual Explanations for Models of Code","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2306.13103","title":"Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks","created":"2023-06-16","cited_by_count":24,"area":"diffusion"},{"id":"2204.10810","title":"Learning to Scaffold: Optimizing Model Explanations for Teaching","created":"2022-04-22","cited_by_count":20,"area":null},{"id":"2205.10226","title":"Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?","created":"2022-04-25","cited_by_count":20,"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":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2305.15587","title":"How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks","created":"2023-05-24","cited_by_count":18,"area":null},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17,"area":null},{"id":"2108.08375","title":"Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks","created":"2021-08-18","cited_by_count":16,"area":null},{"id":"2110.07550","title":"The Irrationality of Neural Rationale Models","created":"2021-10-14","cited_by_count":16,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2205.11097","title":"A Fine-grained Interpretability Evaluation Benchmark for Neural NLP","created":"2022-05-23","cited_by_count":15,"area":null},{"id":"2206.03178","title":"Fooling Explanations in Text Classifiers","created":"2022-06-07","cited_by_count":13,"area":null},{"id":"2306.04954","title":"RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction","created":"2023-06-08","cited_by_count":13,"area":null},{"id":"2405.20701","title":"Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2104.07921","title":"VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2104.12567","title":"Evaluating the Values of Sources in Transfer Learning","created":"2021-04-26","cited_by_count":11,"area":null},{"id":"2106.09558","title":"Element Intervention for Open Relation Extraction","created":"2021-06-17","cited_by_count":11,"area":null},{"id":"2205.08696","title":"The Solvability of Interpretability Evaluation Metrics","created":"2022-05-18","cited_by_count":11,"area":null},{"id":"2408.08137","title":"Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2108.00578","title":"Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning","created":"2021-08-02","cited_by_count":9,"area":null},{"id":"2109.07983","title":"Let the CAT out of the bag: Contrastive Attributed explanations for Text","created":"2021-09-16","cited_by_count":9,"area":null},{"id":"2304.11721","title":"A Lightweight Constrained Generation Alternative for Query-focused Summarization","created":"2023-04-23","cited_by_count":8,"area":null},{"id":"2305.15015","title":"Measuring Faithful and Plausible Visual Grounding in VQA","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2305.16444","title":"Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text","created":"2023-05-25","cited_by_count":8,"area":null},{"id":"2312.01582","title":"Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences","created":"2023-12-04","cited_by_count":8,"area":null},{"id":"2401.09972","title":"Better Explain Transformers by Illuminating Important Information","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2107.07970","title":"How Vulnerable Are Automatic Fake News Detection Methods to Adversarial Attacks?","created":"2021-07-16","cited_by_count":7,"area":null},{"id":"2110.03949","title":"CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learning","created":"2021-10-08","cited_by_count":7,"area":null},{"id":"2302.09665","title":"CitySpec with Shield: A Secure Intelligent Assistant for Requirement Formalization","created":"2023-02-19","cited_by_count":7,"area":null},{"id":"2406.16342","title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2111.04260","title":"Personalized Benchmarking with the Ludwig Benchmarking Toolkit","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2305.06841","title":"Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models","created":"2023-05-11","cited_by_count":6,"area":"lr"},{"id":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2102.00238","title":"ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models","created":"2021-01-30","cited_by_count":5,"area":null},{"id":"2104.07249","title":"Regularization for Long Named Entity Recognition","created":"2021-04-15","cited_by_count":5,"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":"2110.11929","title":"Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?","created":"2021-10-22","cited_by_count":5,"area":null},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2307.07160","title":"Do not Mask Randomly: Effective Domain-adaptive Pre-training by Masking In-domain Keywords","created":"2023-07-14","cited_by_count":5,"area":null},{"id":"2311.00508","title":"Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2312.13616","title":"Navigating the Structured What-If Spaces: Counterfactual Generation via Structured Diffusion","created":"2023-12-21","cited_by_count":5,"area":"diffusion"},{"id":"2207.13948","title":"An Interpretability Evaluation Benchmark for Pre-trained Language Models","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2210.05883","title":"AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning","created":"2022-10-12","cited_by_count":4,"area":null},{"id":"2310.14418","title":"REFER: An End-to-end Rationale Extraction Framework for Explanation Regularization","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2406.10085","title":"Enhancing Question Answering on Charts Through Effective Pre-training Tasks","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2502.12992","title":"B-cos LM: Efficiently Transforming Pre-trained Language Models for Improved Explainability","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2505.08080","title":"Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders","created":"2025-05-12","cited_by_count":4,"area":"mechinterp"},{"id":"2103.14973","title":"Explaining the Road Not Taken","created":"2021-03-27","cited_by_count":3,"area":null},{"id":"2209.02145","title":"Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English","created":"2022-09-05","cited_by_count":3,"area":null},{"id":"2210.11498","title":"Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models","created":"2022-10-20","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":"2307.12507","title":"Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2310.14001","title":"Toward Stronger Textual Attack Detectors","created":"2023-10-21","cited_by_count":3,"area":null},{"id":"2402.03477","title":"Arabic Synonym BERT-based Adversarial Examples for Text Classification","created":"2024-02-05","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":"2511.10439","title":"Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2101.08523","title":"Adv-OLM: Generating Textual Adversaries via OLM","created":"2021-01-21","cited_by_count":2,"area":null},{"id":"2104.07894","title":"Faithful and Plausible Explanations of Medical Code Predictions","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2109.06181","title":"When Stability meets Sufficiency: Informative Explanations that do not Overwhelm","created":"2021-09-13","cited_by_count":2,"area":null},{"id":"2110.07686","title":"Making Document-Level Information Extraction Right for the Right Reasons","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2112.12444","title":"More Than Words: Towards Better Quality Interpretations of Text Classifiers","created":"2021-12-23","cited_by_count":2,"area":null},{"id":"2201.03742","title":"Explaining Predictive Uncertainty by Looking Back at Model Explanations","created":"2022-01-11","cited_by_count":2,"area":null},{"id":"2203.12298","title":"Input-specific Attention Subnetworks for Adversarial Detection","created":"2022-03-23","cited_by_count":2,"area":null},{"id":"2205.11551","title":"Learning to Ignore Adversarial Attacks","created":"2022-05-23","cited_by_count":2,"area":null},{"id":"2206.02761","title":"Dual Decomposition of Convex Optimization Layers for Consistent Attention in Medical Images","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2208.09316","title":"UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA","created":"2022-08-19","cited_by_count":2,"area":null},{"id":"2211.03046","title":"Knowledge is Power: Understanding Causality Makes Legal judgment Prediction Models More Generalizable and Robust","created":"2022-11-06","cited_by_count":2,"area":null},{"id":"2307.12520","title":"Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation","created":"2023-07-24","cited_by_count":2,"area":null},{"id":"2312.10942","title":"ShuttleSHAP: A Turn-Based Feature Attribution Approach for Analyzing Forecasting Models in Badminton","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2401.03253","title":"VLLaVO: Mitigating Visual Gap through LLMs","created":"2024-01-06","cited_by_count":2,"area":"mllm"},{"id":"2408.10528","title":"NoMatterXAI: Generating \"No Matter What\" Alterfactual Examples for Explaining Black-Box Text Classification Models","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2409.17774","title":"Faithfulness and the Notion of Adversarial Sensitivity in NLP Explanations","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2502.03418","title":"Which Words Matter Most in Zero-Shot Prompts?","created":"2025-02-05","cited_by_count":2,"area":null}],"next_cursor":"100"}