{"total":224,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"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":"2110.10790","title":"Human-Centered Explainable AI (XAI): From Algorithms to User Experiences","created":"2021-10-20","cited_by_count":123,"area":null},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109,"area":null},{"id":"2202.10419","title":"Interpreting Language Models with Contrastive Explanations","created":"2022-02-21","cited_by_count":92,"area":null},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90,"area":"lr"},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"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":"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":"2105.13562","title":"ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation","created":"2021-05-28","cited_by_count":78,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66,"area":"safety"},{"id":"2211.01562","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","created":"2022-11-03","cited_by_count":56,"area":"lr"},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2106.08367","title":"What Context Features Can Transformer Language Models Use?","created":"2021-06-15","cited_by_count":50,"area":null},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50,"area":null},{"id":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48,"area":null},{"id":"2108.13654","title":"Discretized Integrated Gradients for Explaining Language Models","created":"2021-08-31","cited_by_count":46,"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":"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":"2111.08446","title":"Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions","created":"2021-11-03","cited_by_count":43,"area":null},{"id":"2201.12114","title":"Rethinking Attention-Model Explainability through Faithfulness Violation Test","created":"2022-01-28","cited_by_count":43,"area":null},{"id":"2305.12535","title":"Explaining How Transformers Use Context to Build Predictions","created":"2023-05-21","cited_by_count":43,"area":null},{"id":"2203.16747","title":"How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis","created":"2022-03-31","cited_by_count":42,"area":null},{"id":"2605.05726","title":"SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents","created":"2026-05-07","cited_by_count":39,"area":"agents"},{"id":"2210.06929","title":"On the Explainability of Natural Language Processing Deep Models","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2104.05824","title":"Evaluating Saliency Methods for Neural Language Models","created":"2021-04-12","cited_by_count":37,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"area":null},{"id":"2111.07668","title":"Fast Axiomatic Attribution for Neural Networks","created":"2021-11-15","cited_by_count":35,"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":"2102.05456","title":"Civil Rephrases Of Toxic Texts With Self-Supervised Transformers","created":"2021-02-01","cited_by_count":32,"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":"2208.10609","title":"Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis","created":"2022-08-22","cited_by_count":32,"area":null},{"id":"2311.03533","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models","created":"2023-11-06","cited_by_count":32,"area":null},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2105.14652","title":"Attention Flows are Shapley Value Explanations","created":"2021-05-31","cited_by_count":30,"area":null},{"id":"2108.04990","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","created":"2021-08-11","cited_by_count":30,"area":null},{"id":"2101.04109","title":"Explain and Predict, and then Predict Again","created":"2021-01-11","cited_by_count":29,"area":null},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29,"area":null},{"id":"2311.09060","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","created":"2023-11-15","cited_by_count":29,"area":null},{"id":"2211.03064","title":"ViT-CX: Causal Explanation of Vision Transformers","created":"2022-11-06","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":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2111.05711","title":"Counterfactual Explanations for Models of Code","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2411.15102","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","created":"2024-11-22","cited_by_count":23,"area":null},{"id":"2106.03471","title":"Relative Importance in Sentence Processing","created":"2021-06-07","cited_by_count":22,"area":null},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","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":"2109.05463","title":"Logic Traps in Evaluating Attribution Scores","created":"2021-09-12","cited_by_count":18,"area":null},{"id":"2108.13759","title":"Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience","created":"2021-08-31","cited_by_count":16,"area":null},{"id":"2408.09121","title":"Selective Prompt Anchoring for Code Generation","created":"2024-08-17","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":"2205.11097","title":"A Fine-grained Interpretability Evaluation Benchmark for Neural NLP","created":"2022-05-23","cited_by_count":15,"area":null},{"id":"2305.14582","title":"Interpretation of Time-Series Deep Models: A Survey","created":"2023-05-23","cited_by_count":15,"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":"2306.01220","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2205.04559","title":"A Song of (Dis)agreement: Evaluating the Evaluation of Explainable Artificial Intelligence in Natural Language Processing","created":"2022-05-09","cited_by_count":13,"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":"2408.11727","title":"Efficient Detection of Toxic Prompts in Large Language Models","created":"2024-08-21","cited_by_count":13,"area":null},{"id":"2104.04488","title":"Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks","created":"2021-04-09","cited_by_count":12,"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":"2206.11212","title":"VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives","created":"2022-06-22","cited_by_count":12,"area":"lr"},{"id":"2104.12567","title":"Evaluating the Values of Sources in Transfer Learning","created":"2021-04-26","cited_by_count":11,"area":null},{"id":"2105.04181","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","created":"2021-05-10","cited_by_count":11,"area":"distill"},{"id":"2108.13587","title":"T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP","created":"2021-08-31","cited_by_count":11,"area":null},{"id":"2108.13961","title":"Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools","created":"2021-08-31","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":"2210.11528","title":"Unsupervised Text Deidentification","created":"2022-10-20","cited_by_count":11,"area":null},{"id":"2405.05386","title":"Interpretability Needs a New Paradigm","created":"2024-05-08","cited_by_count":11,"area":null},{"id":"2502.15886","title":"A Close Look at Decomposition-based XAI-Methods for Transformer Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","cited_by_count":10,"area":null},{"id":"2605.01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","created":"2026-05-01","cited_by_count":10,"area":null},{"id":"2503.02003","title":"HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs","created":"2025-03-03","cited_by_count":9,"area":"lr"},{"id":"2103.12983","title":"Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction","created":"2021-03-24","cited_by_count":8,"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":"2206.04800","title":"Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey","created":"2022-06-07","cited_by_count":8,"area":null},{"id":"2301.12608","title":"Evaluating Neuron Interpretation Methods of NLP Models","created":"2023-01-30","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":"2310.01162","title":"DINE: Dimensional Interpretability of Node Embeddings","created":"2023-10-02","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":"2407.11910","title":"Benchmarking the Attribution Quality of Vision Models","created":"2024-07-16","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":"2110.03949","title":"CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learning","created":"2021-10-08","cited_by_count":7,"area":null},{"id":"2401.17809","title":"SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering","created":"2024-01-31","cited_by_count":7,"area":null},{"id":"2402.17013","title":"Towards Explainability and Fairness in Swiss Judgement Prediction: Benchmarking on a Multilingual Dataset","created":"2024-02-26","cited_by_count":7,"area":null},{"id":"2602.09331","title":"Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2106.15820","title":"Explanation-Guided Diagnosis of Machine Learning Evasion Attacks","created":"2021-06-30","cited_by_count":6,"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":"2405.11891","title":"Unveiling and Manipulating Prompt Influence in Large Language Models","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2410.14391","title":"Context-Aware or Context-Insensitive? Assessing LLMs' Performance in Document-Level Translation","created":"2024-10-18","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":"2107.01791","title":"Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models","created":"2021-07-05","cited_by_count":5,"area":null}],"next_cursor":"100"}