{"total":34,"rows":[{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"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":"2407.15248","title":"XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models","created":"2024-07-21","cited_by_count":23,"area":null},{"id":"2502.17898","title":"VeriPlan: Integrating Formal Verification and LLMs into End-User Planning","created":"2025-02-25","cited_by_count":20,"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":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"area":null},{"id":"2403.05075","title":"Benchmarking Large Language Models for Molecule Prediction Tasks","created":"2024-03-08","cited_by_count":17,"area":null},{"id":"2405.20331","title":"CoSy: Evaluating Textual Explanations of Neurons","created":"2024-05-30","cited_by_count":17,"area":null},{"id":"2311.02801","title":"On the Intersection of Self-Correction and Trust in Language Models","created":"2023-11-06","cited_by_count":12,"area":null},{"id":"2309.16573","title":"Language Models as a Service: Overview of a New Paradigm and its Challenges","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2505.22823","title":"Self-Critique and Refinement for Faithful Natural Language Explanations","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2408.09172","title":"Unlocking the Power of LLM Uncertainty for Active In-Context Example Selection","created":"2024-08-17","cited_by_count":9,"area":null},{"id":"2410.13826","title":"Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2402.12038","title":"Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations","created":"2024-02-19","cited_by_count":8,"area":null},{"id":"2505.21740","title":"Counterfactual Simulatability of LLM Explanations for Generation Tasks","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2402.13414","title":"Harnessing Large Language Models as Post-hoc Correctors","created":"2024-02-20","cited_by_count":7,"area":null},{"id":"2406.02625","title":"Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2411.05874","title":"Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review","created":"2024-11-07","cited_by_count":6,"area":null},{"id":"2501.00777","title":"FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation","created":"2025-01-01","cited_by_count":6,"area":null},{"id":"2311.07099","title":"Explanation-aware Soft Ensemble Empowers Large Language Model In-context Learning","created":"2023-11-13","cited_by_count":4,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2412.12318","title":"Graph-Guided Textual Explanation Generation Framework","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2503.15564","title":"GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2505.01198","title":"Gender Bias in Explainability: Investigating Performance Disparity in Post-hoc Methods","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2509.26543","title":"The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models","created":"2025-09-30","cited_by_count":3,"area":null},{"id":"2511.16353","title":"Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2408.04689","title":"Design of a Quality Management System based on the EU Artificial Intelligence Act","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2411.05991","title":"GUIDEQ: Framework for Guided Questioning for progressive informational collection and classification","created":"2024-11-08","cited_by_count":0,"area":null},{"id":"2504.08919","title":"Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2507.10596","title":"PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2512.22508","title":"Predicting LLM Correctness in Prosthodontics Using Metadata and Hallucination Signals","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2608.07481","title":"Cross-Model Humor Preference Modeling with Cards Against Humanity","created":"2026-06-09","cited_by_count":0,"area":null}],"next_cursor":null}