{"total":126,"rows":[{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156,"area":null},{"id":"2209.05364","title":"If Influence Functions are the Answer, Then What is the Question?","created":"2022-09-12","cited_by_count":144,"area":null},{"id":"2112.03052","title":"Scaling Up Influence Functions","created":"2021-12-06","cited_by_count":132,"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":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"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":"2302.11042","title":"In-context Example Selection with Influences","created":"2023-02-21","cited_by_count":61,"area":null},{"id":"2212.04629","title":"Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation","created":"2022-12-09","cited_by_count":59,"area":null},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2108.11357","title":"ProoFVer: Natural Logic Theorem Proving for Fact Verification","created":"2021-08-25","cited_by_count":53,"area":null},{"id":"2303.08114","title":"Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs","created":"2023-03-14","cited_by_count":53,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44,"area":null},{"id":"2107.00323","title":"Combining Feature and Instance Attribution to Detect Artifacts","created":"2021-07-01","cited_by_count":38,"area":null},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2104.04128","title":"An Empirical Comparison of Instance Attribution Methods for NLP","created":"2021-04-09","cited_by_count":35,"area":null},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2202.11844","title":"First is Better Than Last for Language Data Influence","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2205.12600","title":"ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data","created":"2022-05-25","cited_by_count":34,"area":null},{"id":"2405.12186","title":"Training Data Attribution via Approximate Unrolled Differentiation","created":"2024-05-20","cited_by_count":34,"area":null},{"id":"2203.01311","title":"High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning","created":"2022-03-02","cited_by_count":31,"area":null},{"id":"2405.12915","title":"G-DIG: Towards Gradient-based Diverse and High-quality Instruction Data Selection for Machine Translation","created":"2024-05-21","cited_by_count":30,"area":null},{"id":"2104.01477","title":"Exploring the Role of BERT Token Representations to Explain Sentence Probing Results","created":"2021-04-03","cited_by_count":29,"area":null},{"id":"2110.03212","title":"Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2504.07096","title":"OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens","created":"2025-04-09","cited_by_count":27,"area":null},{"id":"2405.15476","title":"Editable Concept Bottleneck Models","created":"2024-05-24","cited_by_count":23,"area":null},{"id":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2203.12171","title":"An Empirical Study of Memorization in NLP","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2205.11482","title":"Towards Tracing Factual Knowledge in Language Models Back to the Training Data","created":"2022-05-23","cited_by_count":21,"area":null},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2303.12922","title":"Revisiting the Fragility of Influence Functions","created":"2023-03-22","cited_by_count":20,"area":null},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","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":"2302.13959","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2310.12127","title":"A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation","created":"2023-10-18","cited_by_count":19,"area":null},{"id":"2109.12761","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2210.07441","title":"Characterizing the Influence of Graph Elements","created":"2022-10-14","cited_by_count":16,"area":null},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"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":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2210.11560","title":"Finding Dataset Shortcuts with Grammar Induction","created":"2022-10-20","cited_by_count":15,"area":null},{"id":"2306.13041","title":"Towards Explainable Evaluation Metrics for Machine Translation","created":"2023-06-22","cited_by_count":15,"area":null},{"id":"2305.13286","title":"How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning","created":"2023-05-22","cited_by_count":14,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"area":null},{"id":"2311.08273","title":"Examining Modularity in Multilingual LMs via Language-Specialized Subnetworks","created":"2023-11-14","cited_by_count":13,"area":null},{"id":"2106.04753","title":"On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation","created":"2021-06-09","cited_by_count":12,"area":null},{"id":"2212.10722","title":"Contrastive Error Attribution for Finetuned Language Models","created":"2022-12-21","cited_by_count":12,"area":null},{"id":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2402.11750","title":"In-Context Learning Demonstration Selection via Influence Analysis","created":"2024-02-19","cited_by_count":11,"area":null},{"id":"2106.01518","title":"Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution","created":"2021-06-03","cited_by_count":10,"area":null},{"id":"2302.02169","title":"How Many and Which Training Points Would Need to be Removed to Flip this Prediction?","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","cited_by_count":10,"area":null},{"id":"2405.03869","title":"Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2405.12744","title":"The Echoes of Multilinguality: Tracing Cultural Value Shifts during LM Fine-tuning","created":"2024-05-21","cited_by_count":10,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2210.14177","title":"Influence Functions for Sequence Tagging Models","created":"2022-10-25","cited_by_count":9,"area":null},{"id":"2404.18655","title":"Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods","created":"2024-04-29","cited_by_count":9,"area":null},{"id":"2303.03124","title":"IFAN: An Explainability-Focused Interaction Framework for Humans and NLP Models","created":"2023-03-06","cited_by_count":8,"area":null},{"id":"2411.11667","title":"Dissecting Representation Misalignment in Contrastive Learning via Influence Function","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2310.02533","title":"Quantifying and mitigating the impact of label errors on model disparity metrics","created":"2023-10-04","cited_by_count":7,"area":null},{"id":"2605.11161","title":"Interpretability Can Be Actionable","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2104.03958","title":"GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2310.00840","title":"Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models","created":"2023-10-02","cited_by_count":6,"area":null},{"id":"2310.15055","title":"Towards Conceptualization of \"Fair Explanation\": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2505.07853","title":"CrashSage: A Large Language Model-Centered Framework for Contextual and Interpretable Traffic Crash Analysis","created":"2025-05-08","cited_by_count":6,"area":null},{"id":"2203.08670","title":"Measuring Fairness of Text Classifiers via Prediction Sensitivity","created":"2022-03-16","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":"2307.03056","title":"Generalizing Backpropagation for Gradient-Based Interpretability","created":"2023-07-06","cited_by_count":5,"area":null},{"id":"2406.08101","title":"CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2508.08274","title":"Distilling Knowledge from Large Language Models: A Concept Bottleneck Model for Hate and Counter Speech Recognition","created":"2025-07-30","cited_by_count":5,"area":null},{"id":"2511.04715","title":"First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation","created":"2025-11-06","cited_by_count":5,"area":null},{"id":"2104.00312","title":"Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2110.02058","title":"Interactively Providing Explanations for Transformer Language Models","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2202.08048","title":"Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective","created":"2022-02-16","cited_by_count":4,"area":null},{"id":"2202.09096","title":"A Free Lunch with Influence Functions? Improving Neural Network Estimates with Concepts from Semiparametric Statistics","created":"2022-02-18","cited_by_count":4,"area":null},{"id":"2206.11155","title":"Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses","created":"2022-06-22","cited_by_count":4,"area":null},{"id":"2210.13439","title":"Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2505.19097","title":"Towards Robust Influence Functions with Flat Validation Minima","created":"2025-05-25","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":"2110.08931","title":"Quantifying the Task-Specific Information in Text-Based Classifications","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2210.13281","title":"Analyzing the Use of Influence Functions for Instance-Specific Data Filtering in Neural Machine Translation","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2305.12809","title":"Relabeling Minimal Training Subset to Flip a Prediction","created":"2023-05-22","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":"2501.01473","title":"Unraveling Indirect In-Context Learning Using Influence Functions","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2506.04694","title":"Influence Functions for Edge Edits in Non-Convex Graph Neural Networks","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2606.11660","title":"Bergson: An Open Source Library for Data Attribution","created":"2026-06-10","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":"2202.09875","title":"Trying to Outrun Causality with Machine Learning: Limitations of Model Explainability Techniques for Identifying Predictive Variables","created":"2022-02-20","cited_by_count":2,"area":null},{"id":"2211.05452","title":"Towards Human-Centred Explainability Benchmarks For Text Classification","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2301.09912","title":"Applications and Challenges of Sentiment Analysis in Real-life Scenarios","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2304.13010","title":"Unstructured and structured data: Can we have the best of both worlds with large language models?","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2307.09615","title":"Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey","created":"2023-07-14","cited_by_count":2,"area":null},{"id":"2312.09718","title":"Discovering Highly Influential Shortcut Reasoning: An Automated Template-Free Approach","created":"2023-12-15","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":"2407.08169","title":"The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models","created":"2024-07-11","cited_by_count":2,"area":null}],"next_cursor":"100"}