{"total":23,"rows":[{"id":"2402.12865","title":"Backward Lens: Projecting Language Model Gradients into the Vocabulary Space","created":"2024-02-20","cited_by_count":32,"area":null},{"id":"2406.18841","title":"Navigating LLM Ethics: Advancements, Challenges, and Future Directions","created":"2024-05-14","cited_by_count":28,"area":null},{"id":"2404.07004","title":"LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models","created":"2024-04-10","cited_by_count":16,"area":null},{"id":"2402.02631","title":"Learning to Understand: Identifying Interactions via the M\\\"obius Transform","created":"2024-02-04","cited_by_count":13,"area":null},{"id":"2506.04202","title":"TracLLM: A Generic Framework for Attributing Long Context LLMs","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2402.09259","title":"SyntaxShap: Syntax-aware Explainability Method for Text Generation","created":"2024-02-14","cited_by_count":11,"area":null},{"id":"2403.14459","title":"Multi-Level Explanations for Generative Language Models","created":"2024-03-21","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":"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":"2502.11100","title":"Towards Achieving Concept Completeness for Textual Concept Bottleneck Models","created":"2025-02-16","cited_by_count":7,"area":null},{"id":"2404.07498","title":"Interactive Prompt Debugging with Sequence Salience","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2405.20404","title":"JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution","created":"2024-05-30","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":"2403.10831","title":"DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation","created":"2024-03-16","cited_by_count":4,"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":"2405.19562","title":"Selective Explanations","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2409.13764","title":"Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2505.01238","title":"EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2602.00092","title":"Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2407.19055","title":"Effective Large Language Model Debugging with Best-first Tree Search","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2505.06324","title":"Document Attribution: Examining Citation Relationships using Large Language Models","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2601.04548","title":"Identifying Good and Bad Neurons for Task-Level Controllable LLMs","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2604.15589","title":"LLM attribution analysis across different fine-tuning strategies and model scales for automated code compliance","created":"2026-04-16","cited_by_count":1,"area":null}],"next_cursor":null}