{"total":206,"rows":[{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876,"area":null},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668,"area":null},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2305.00050","title":"Causal Reasoning and Large Language Models: Opening a New Frontier for Causality","created":"2023-04-28","cited_by_count":353,"area":"lr"},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249,"area":null},{"id":"2212.07919","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","created":"2022-12-15","cited_by_count":177,"area":"lr"},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"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":"2102.13076","title":"Benchmarking and Survey of Explanation Methods for Black Box Models","created":"2021-02-25","cited_by_count":136,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125,"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":"2204.08570","title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","created":"2022-04-18","cited_by_count":118,"area":null},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104,"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":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2105.07190","title":"A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts","created":"2021-05-15","cited_by_count":91,"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":"2308.09729","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","created":"2023-08-17","cited_by_count":73,"area":"lr"},{"id":"2307.03875","title":"Large Language Models for Supply Chain Optimization","created":"2023-07-08","cited_by_count":64,"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":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","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":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2407.10114","title":"TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation","created":"2024-07-14","cited_by_count":42,"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":"2206.07023","title":"SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features","created":"2022-06-14","cited_by_count":33,"area":null},{"id":"2405.09308","title":"TimeX++: Learning Time-Series Explanations with Information Bottleneck","created":"2024-05-15","cited_by_count":33,"area":null},{"id":"2112.11407","title":"Toward Explainable AI for Regression Models","created":"2021-12-21","cited_by_count":31,"area":null},{"id":"2301.08110","title":"AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation","created":"2023-01-19","cited_by_count":31,"area":null},{"id":"2503.07513","title":"Language Models Fail to Introspect About Their Knowledge of Language","created":"2025-03-10","cited_by_count":30,"area":null},{"id":"2110.04392","title":"The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results","created":"2021-10-08","cited_by_count":27,"area":null},{"id":"2205.09224","title":"Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner","created":"2022-05-18","cited_by_count":26,"area":"lr"},{"id":"2208.01575","title":"ferret: a Framework for Benchmarking Explainers on Transformers","created":"2022-08-02","cited_by_count":26,"area":null},{"id":"2105.02590","title":"Reliability Testing for Natural Language Processing Systems","created":"2021-05-06","cited_by_count":25,"area":null},{"id":"2110.04399","title":"Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors","created":"2021-10-08","cited_by_count":25,"area":null},{"id":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","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":"2505.17120","title":"Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2210.13836","title":"Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts","created":"2022-10-25","cited_by_count":24,"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":"2301.08912","title":"Rationalization for Explainable NLP: A Survey","created":"2023-01-21","cited_by_count":22,"area":null},{"id":"2204.05426","title":"ProtoTEx: Explaining Model Decisions with Prototype Tensors","created":"2022-04-11","cited_by_count":21,"area":null},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"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":"2306.14115","title":"Towards Trustworthy Explanation: On Causal Rationalization","created":"2023-06-25","cited_by_count":19,"area":null},{"id":"2409.17270","title":"Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning","created":"2024-09-25","cited_by_count":19,"area":"lr"},{"id":"2205.03302","title":"Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection","created":"2022-05-06","cited_by_count":18,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2305.18727","title":"An Annotated Dataset for Explainable Interpersonal Risk Factors of Mental Disturbance in Social Media Posts","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2402.04978","title":"An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration","created":"2024-02-07","cited_by_count":16,"area":"lr"},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","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":"2502.04577","title":"Position-aware Automatic Circuit Discovery","created":"2025-02-07","cited_by_count":14,"area":"mechinterp"},{"id":"2302.06729","title":"STREET: A Multi-Task Structured Reasoning and Explanation Benchmark","created":"2023-02-13","cited_by_count":13,"area":"lr"},{"id":"2304.11218","title":"Explainability in AI Policies: A Critical Review of Communications, Reports, Regulations, and Standards in the EU, US, and UK","created":"2023-04-20","cited_by_count":13,"area":null},{"id":"2502.14862","title":"Interpretable Text Embeddings and Text Similarity Explanation: A Survey","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2106.09795","title":"LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking","created":"2021-06-17","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":"2205.12469","title":"Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI","created":"2022-05-25","cited_by_count":11,"area":null},{"id":"2403.11894","title":"From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?","created":"2024-03-18","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2110.09599","title":"Label-Descriptive Patterns and Their Application to Characterizing Classification Errors","created":"2021-10-18","cited_by_count":10,"area":null},{"id":"2305.18011","title":"Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2309.11960","title":"A Comprehensive Review on Financial Explainable AI","created":"2023-09-21","cited_by_count":10,"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":"2502.03688","title":"A Comparison of DeepSeek and Other LLMs","created":"2025-02-06","cited_by_count":10,"area":null},{"id":"2502.19190","title":"Provocations from the Humanities for Generative AI Research","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2506.05035","title":"TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation","created":"2025-06-05","cited_by_count":10,"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":"2301.04528","title":"The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2303.12942","title":"A Survey on Explainable Artificial Intelligence for Cybersecurity","created":"2023-03-07","cited_by_count":9,"area":null},{"id":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2205.07750","title":"What company do words keep? Revisiting the distributional semantics of J.R. Firth & Zellig Harris","created":"2022-05-16","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":"2310.05703","title":"An Attribution Method for Siamese Encoders","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2304.14094","title":"Categorical Foundations of Explainable AI: A Unifying Theory","created":"2023-04-27","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2307.10652","title":"Exploring the Landscape of Natural Language Processing Research","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2402.02883","title":"Approximate Attributions for Off-the-Shelf Siamese Transformers","created":"2024-02-05","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":"2412.00800","title":"A Comprehensive Guide to Explainable AI: From Classical Models to LLMs","created":"2024-12-01","cited_by_count":7,"area":null},{"id":"2205.13789","title":"A Sea of Words: An In-Depth Analysis of Anchors for Text Data","created":"2022-05-27","cited_by_count":6,"area":null},{"id":"2210.08430","title":"Explainable Causal Analysis of Mental Health on Social Media Data","created":"2022-10-16","cited_by_count":6,"area":null},{"id":"2210.10689","title":"Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information","created":"2022-10-19","cited_by_count":6,"area":null},{"id":"2301.05433","title":"Trends in Explainable AI (XAI) Literature","created":"2023-01-13","cited_by_count":6,"area":null},{"id":"2310.11252","title":"Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges","created":"2023-10-17","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":"2403.03028","title":"Word Importance Explains How Prompts Affect Language Model Outputs","created":"2024-03-05","cited_by_count":6,"area":null},{"id":"2404.04728","title":"Navigating the Landscape of Hint Generation Research: From the Past to the Future","created":"2024-04-06","cited_by_count":6,"area":null},{"id":"2406.05984","title":"Explainable AI for Mental Disorder Detection via Social Media: A survey and outlook","created":"2024-06-10","cited_by_count":6,"area":null},{"id":"2411.01710","title":"SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation","created":"2024-11-03","cited_by_count":6,"area":null},{"id":"2505.07610","title":"Concept-Level Explainability for Auditing & Steering LLM Responses","created":"2025-05-12","cited_by_count":6,"area":"safety"},{"id":"2505.14469","title":"Attributional Safety Failures in Large Language Models under Code-Mixed Perturbations","created":"2025-05-20","cited_by_count":6,"area":"safety"},{"id":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2109.15004","title":"XPROAX-Local explanations for text classification with progressive neighborhood approximation","created":"2021-09-30","cited_by_count":5,"area":null},{"id":"2204.05428","title":"A Multilingual Perspective Towards the Evaluation of Attribution Methods in Natural Language Inference","created":"2022-04-11","cited_by_count":5,"area":null}],"next_cursor":"100"}